Publications
2021
Errica, Federico; Bacciu, Davide; Micheli, Alessio
Graph Mixture Density Networks Conference
Proceedings of the 38th International Conference on Machine Learning (ICML 2021), PMLR, 2021.
Links | BibTeX | Tags: deep learning for graphs, generative model, graph data, structured data processing
@conference{Errica2021,
title = {Graph Mixture Density Networks},
author = {Federico Errica and Davide Bacciu and Alessio Micheli},
url = {https://proceedings.mlr.press/v139/errica21a.html, PDF},
year = {2021},
date = {2021-07-18},
urldate = {2021-07-18},
booktitle = {Proceedings of the 38th International Conference on Machine Learning (ICML 2021)},
pages = {3025-3035},
publisher = {PMLR},
keywords = {deep learning for graphs, generative model, graph data, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
Lomonaco, Vincenzo; Pellegrini, Lorenzo; Cossu, Andrea; Carta, Antonio; Graffieti, Gabriele; Hayes, Tyler L; Lange, Matthias De; Masana, Marc; Pomponi, Jary; van de Ven, Gido; Mundt, Martin; She, Qi; Cooper, Keiland; Forest, Jeremy; Belouadah, Eden; Calderara, Simone; Parisi, German I; Cuzzolin, Fabio; Tolias, Andreas; Scardapane, Simone; Antiga, Luca; Amhad, Subutai; Popescu, Adrian; Kanan, Christopher; van de Weijer, Joost; Tuytelaars, Tinne; Bacciu, Davide; Maltoni, Davide
Avalanche: an End-to-End Library for Continual Learning Workshop
Proceedings of the CVPR 2021 Workshop on Continual Learning , IEEE, 2021.
Links | BibTeX | Tags: Continual learning, deep learning, software
@workshop{lomonaco2021avalanche,
title = {Avalanche: an End-to-End Library for Continual Learning},
author = {Vincenzo Lomonaco and Lorenzo Pellegrini and Andrea Cossu and Antonio Carta and Gabriele Graffieti and Tyler L Hayes and Matthias De Lange and Marc Masana and Jary Pomponi and Gido van de Ven and Martin Mundt and Qi She and Keiland Cooper and Jeremy Forest and Eden Belouadah and Simone Calderara and German I Parisi and Fabio Cuzzolin and Andreas Tolias and Simone Scardapane and Luca Antiga and Subutai Amhad and Adrian Popescu and Christopher Kanan and Joost van de Weijer and Tinne Tuytelaars and Davide Bacciu and Davide Maltoni},
url = {https://arxiv.org/abs/2104.00405, Arxiv},
year = {2021},
date = {2021-06-19},
urldate = {2021-06-19},
booktitle = {Proceedings of the CVPR 2021 Workshop on Continual Learning },
pages = {3600-3610},
publisher = {IEEE},
keywords = {Continual learning, deep learning, software},
pubstate = {published},
tppubtype = {workshop}
}
Sattar, Asma; Bacciu, Davide
Context-aware Graph Convolutional Autoencoder Conference
Proceedings of the 16th International Work Conference on Artificial Neural Networks (IWANN 2021), vol. 12862, LNCS Springer, 2021.
Abstract | Links | BibTeX | Tags: deep learning for graphs, graph data, recommendation systems
@conference{Sattar2021,
title = {Context-aware Graph Convolutional Autoencoder},
author = {Asma Sattar and Davide Bacciu
},
doi = {10.1007/978-3-030-85030-2_23},
year = {2021},
date = {2021-06-16},
urldate = {2021-06-16},
booktitle = {Proceedings of the 16th International Work Conference on Artificial Neural Networks (IWANN 2021)},
volume = {12862},
pages = { 279-290},
publisher = {Springer},
series = {LNCS},
abstract = {Recommendation problems can be addressed as link prediction tasks in a bipartite graph between user and item nodes, labelled with rating on edges. Existing matrix completion approaches model the user’s opinion on items by ignoring context information that can instead be associated with the edges of the bipartite graph. Context is an important factor to be considered as it heavily affects opinions and preferences. Following this line of research, this paper proposes a graph convolutional auto-encoder approach which considers users’ opinion on items as well as the static node features and context information on edges. Our graph encoder produces a representation of users and items from the perspective of context, static features, and rating opinion. The empirical analysis on three real-world datasets shows that the proposed approach outperforms recent state-of-the-art recommendation systems.},
keywords = {deep learning for graphs, graph data, recommendation systems},
pubstate = {published},
tppubtype = {conference}
}
Recommendation problems can be addressed as link prediction tasks in a bipartite graph between user and item nodes, labelled with rating on edges. Existing matrix completion approaches model the user’s opinion on items by ignoring context information that can instead be associated with the edges of the bipartite graph. Context is an important factor to be considered as it heavily affects opinions and preferences. Following this line of research, this paper proposes a graph convolutional auto-encoder approach which considers users’ opinion on items as well as the static node features and context information on edges. Our graph encoder produces a representation of users and items from the perspective of context, static features, and rating opinion. The empirical analysis on three real-world datasets shows that the proposed approach outperforms recent state-of-the-art recommendation systems. Bacciu, Davide; Sarli, Daniele Di; Gallicchio, Claudio; Micheli, Alessio; Puccinelli, Niccolo
Benchmarking Reservoir and Recurrent Neural Networks for Human State and Activity Recognition Conference
Proceedings of the 16th International Work Conference on Artificial Neural Networks (IWANN 2021), vol. 12862, Springer, 2021.
Abstract | Links | BibTeX | Tags: activity recognition, Echo state networks, recurrent neural network, reservoir computing
@conference{Bacciu2021,
title = {Benchmarking Reservoir and Recurrent Neural Networks for Human State and Activity Recognition},
author = {Davide Bacciu and Daniele Di Sarli and Claudio Gallicchio and Alessio Micheli and Niccolo Puccinelli},
doi = {10.1007/978-3-030-85099-9_14},
year = {2021},
date = {2021-06-16},
urldate = {2021-06-16},
booktitle = {Proceedings of the 16th International Work Conference on Artificial Neural Networks (IWANN 2021)},
volume = {12862},
pages = {168-179},
publisher = {Springer},
abstract = {Monitoring of human states from streams of sensor data is an appealing applicative area for Recurrent Neural Network (RNN) models. In such a scenario, Echo State Network (ESN) models from the Reservoir Computing paradigm can represent good candidates due to the efficient training algorithms, which, compared to fully trainable RNNs, definitely ease embedding on edge devices.
In this paper, we provide an experimental analysis aimed at assessing the performance of ESNs on tasks of human state and activity recognition, in both shallow and deep setups. Our analysis is conducted in comparison with vanilla RNNs, Long Short-Term Memory, Gated Recurrent Units, and their deep variations. Our empirical results on several datasets clearly indicate that, despite their simplicity, ESNs are able to achieve a level of accuracy that is competitive with those models that require full adaptation of the parameters. From a broader perspective, our analysis also points out that recurrent networks can be a first choice for the class of tasks under consideration, in particular in their deep and gated variants.},
keywords = {activity recognition, Echo state networks, recurrent neural network, reservoir computing},
pubstate = {published},
tppubtype = {conference}
}
Monitoring of human states from streams of sensor data is an appealing applicative area for Recurrent Neural Network (RNN) models. In such a scenario, Echo State Network (ESN) models from the Reservoir Computing paradigm can represent good candidates due to the efficient training algorithms, which, compared to fully trainable RNNs, definitely ease embedding on edge devices.
In this paper, we provide an experimental analysis aimed at assessing the performance of ESNs on tasks of human state and activity recognition, in both shallow and deep setups. Our analysis is conducted in comparison with vanilla RNNs, Long Short-Term Memory, Gated Recurrent Units, and their deep variations. Our empirical results on several datasets clearly indicate that, despite their simplicity, ESNs are able to achieve a level of accuracy that is competitive with those models that require full adaptation of the parameters. From a broader perspective, our analysis also points out that recurrent networks can be a first choice for the class of tasks under consideration, in particular in their deep and gated variants. Ferrari, Elisa; Bacciu, Davide
Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss Unpublished
Online on Arxiv, 2021.
Abstract | Links | BibTeX | Tags: bioinformatics, biomedical data, deep learning, trustworthy AI
@unpublished{Ferrari2021,
title = {Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss},
author = {Elisa Ferrari and Davide Bacciu},
url = {https://arxiv.org/abs/2105.06345, Arxiv},
year = {2021},
date = {2021-05-13},
urldate = {2021-05-13},
abstract = {Resilience to class imbalance and confounding biases, together with the assurance of fairness guarantees are highly desirable properties of autonomous decision-making systems with real-life impact. Many different targeted solutions have been proposed to address separately these three problems, however a unifying perspective seems to be missing. With this work, we provide a general formalization, showing that they are different expressions of unbalance. Following this intuition, we formulate a unified loss correction to address issues related to Fairness, Biases and Imbalances (FBI-loss). The correction capabilities of the proposed approach are assessed on three real-world benchmarks, each associated to one of the issues under consideration, and on a family of synthetic data in order to better investigate the effectiveness of our loss on tasks with different complexities. The empirical results highlight that the flexible formulation of the FBI-loss leads also to competitive performances with respect to literature solutions specialised for the single problems.},
howpublished = {Online on Arxiv},
keywords = {bioinformatics, biomedical data, deep learning, trustworthy AI},
pubstate = {published},
tppubtype = {unpublished}
}
Resilience to class imbalance and confounding biases, together with the assurance of fairness guarantees are highly desirable properties of autonomous decision-making systems with real-life impact. Many different targeted solutions have been proposed to address separately these three problems, however a unifying perspective seems to be missing. With this work, we provide a general formalization, showing that they are different expressions of unbalance. Following this intuition, we formulate a unified loss correction to address issues related to Fairness, Biases and Imbalances (FBI-loss). The correction capabilities of the proposed approach are assessed on three real-world benchmarks, each associated to one of the issues under consideration, and on a family of synthetic data in order to better investigate the effectiveness of our loss on tasks with different complexities. The empirical results highlight that the flexible formulation of the FBI-loss leads also to competitive performances with respect to literature solutions specialised for the single problems. Carta, Antonio; Cossu, Andrea; Errica, Federico; Bacciu, Davide
Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification Workshop
The Web Conference 2021 Workshop on Graph Learning Benchmarks (GLB21), 2021.
Abstract | BibTeX | Tags: Continual learning, deep learning for graphs, structured data processing
@workshop{Carta2021,
title = { Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification },
author = {Antonio Carta and Andrea Cossu and Federico Errica and Davide Bacciu},
year = {2021},
date = {2021-04-12},
booktitle = {The Web Conference 2021 Workshop on Graph Learning Benchmarks (GLB21)},
abstract = {In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a tangible impact on performances when applied to graph data. To do so, we experiment with a structure-agnostic model and a deep graph network in a robust and controlled environment on three different datasets. The benchmark is complemented by an investigation on the effect of structure-preserving regularization techniques on catastrophic forgetting. We find that replay is the most effective strategy in so far, which also benefits the most from the use of regularization. Our findings suggest interesting future research at the intersection of the continual and graph representation learning fields. Finally, we provide researchers with a flexible software framework to reproduce our results and carry out further experiments.},
keywords = {Continual learning, deep learning for graphs, structured data processing},
pubstate = {published},
tppubtype = {workshop}
}
In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a tangible impact on performances when applied to graph data. To do so, we experiment with a structure-agnostic model and a deep graph network in a robust and controlled environment on three different datasets. The benchmark is complemented by an investigation on the effect of structure-preserving regularization techniques on catastrophic forgetting. We find that replay is the most effective strategy in so far, which also benefits the most from the use of regularization. Our findings suggest interesting future research at the intersection of the continual and graph representation learning fields. Finally, we provide researchers with a flexible software framework to reproduce our results and carry out further experiments. Errica, Federico; Giulini, Marco; Bacciu, Davide; Menichetti, Roberto; Micheli, Alessio; Potestio, Raffaello
A deep graph network-enhanced sampling approach to efficiently explore the space of reduced representations of proteins Journal Article
In: Frontiers in Molecular Biosciences, vol. 8, pp. 136, 2021.
Links | BibTeX | Tags: deep learning, deep learning for graphs, graph data, structured data processing
@article{errica_deep_2021,
title = {A deep graph network-enhanced sampling approach to efficiently explore the space of reduced representations of proteins},
author = {Federico Errica and Marco Giulini and Davide Bacciu and Roberto Menichetti and Alessio Micheli and Raffaello Potestio},
doi = {10.3389/fmolb.2021.637396},
year = {2021},
date = {2021-02-28},
journal = {Frontiers in Molecular Biosciences},
volume = {8},
pages = {136},
publisher = {Frontiers},
keywords = {deep learning, deep learning for graphs, graph data, structured data processing},
pubstate = {published},
tppubtype = {article}
}
Bontempi, Gianluca; Chavarriaga, Ricardo; Canck, Hans De; Girardi, Emanuela; Hoos, Holger; Kilbane-Dawe, Iarla; Ball, Tonio; Nowé, Ann; Sousa, Jose; Bacciu, Davide; Aldinucci, Marco; Domenico, Manlio De; Saffiotti, Alessandro; Maratea, Marco
The CLAIRE COVID-19 initiative: approach, experiences and recommendations Journal Article
In: Ethics and Information Technology, 2021.
Links | BibTeX | Tags: artificial intelligence, bioinformatics, biomedical data
@article{Bontempi2021,
title = {The CLAIRE COVID-19 initiative: approach, experiences and recommendations},
author = {Gianluca Bontempi and Ricardo Chavarriaga and Hans De Canck and Emanuela Girardi and Holger Hoos and Iarla Kilbane-Dawe and Tonio Ball and Ann Nowé and Jose Sousa and Davide Bacciu and Marco Aldinucci and Manlio De Domenico and Alessandro Saffiotti and Marco Maratea},
doi = {10.1007/s10676-020-09567-7},
year = {2021},
date = {2021-02-09},
journal = {Ethics and Information Technology},
keywords = {artificial intelligence, bioinformatics, biomedical data},
pubstate = {published},
tppubtype = {article}
}
Michele Barsotti Andrea Valenti, Davide Bacciu; Ascari, Luca
A Deep Classifier for Upper-Limbs Motor Anticipation Tasks in an Online BCI Setting Journal Article
In: Bioengineering , 2021.
Links | BibTeX | Tags: autoencoder, biomedical data, deep learning, Sequential data
@article{Valenti2021,
title = {A Deep Classifier for Upper-Limbs Motor Anticipation Tasks in an Online BCI Setting},
author = {Andrea Valenti, Michele Barsotti, Davide Bacciu and Luca Ascari
},
url = {https://www.mdpi.com/2306-5354/8/2/21, Open Access },
doi = {10.3390/bioengineering8020021},
year = {2021},
date = {2021-02-05},
journal = {Bioengineering },
keywords = {autoencoder, biomedical data, deep learning, Sequential data},
pubstate = {published},
tppubtype = {article}
}
Bacciu, Davide; Bertoncini, Gioele; Morelli, Davide
Topographic mapping for quality inspection and intelligent filtering of smart-bracelet data Journal Article
In: Neural Computing Applications, 2021.
Links | BibTeX | Tags: biomedical data, data visualization, explainable AI, internet of things, multivariate time-series, self-organizing map
@article{BacciuNCA2020,
title = {Topographic mapping for quality inspection and intelligent filtering of smart-bracelet data},
author = {Davide Bacciu and Gioele Bertoncini and Davide Morelli},
doi = {10.1007/s00521-020-05600-4},
year = {2021},
date = {2021-01-04},
journal = {Neural Computing Applications},
keywords = {biomedical data, data visualization, explainable AI, internet of things, multivariate time-series, self-organizing map},
pubstate = {published},
tppubtype = {article}
}
Crecchi, Francesco; Melis, Marco; Sotgiu, Angelo; Bacciu, Davide; Biggio, Battista
FADER: Fast Adversarial Example Rejection Journal Article
In: Neurocomputing, 2021, ISSN: 0925-2312.
Links | BibTeX | Tags: adversarial examples, adversarial machine learning, deep learning, detection, evasion attacks, rbf networks
@article{CRECCHI2021,
title = {FADER: Fast Adversarial Example Rejection},
author = {Francesco Crecchi and Marco Melis and Angelo Sotgiu and Davide Bacciu and Battista Biggio},
url = {https://arxiv.org/abs/2010.09119, Arxiv},
doi = {https://doi.org/10.1016/j.neucom.2021.10.082},
issn = {0925-2312},
year = {2021},
date = {2021-01-01},
journal = {Neurocomputing},
keywords = {adversarial examples, adversarial machine learning, deep learning, detection, evasion attacks, rbf networks},
pubstate = {published},
tppubtype = {article}
}
2020
Ronchetti, Matteo; Bacciu, Davide
Generative Tomography Reconstruction Workshop
34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Deep Learning and Inverse Problems, 2020.
Abstract | Links | BibTeX | Tags: adversarial learning, biomedical data, deep learning, generative model, inverse problems, machine vision
@workshop{tomographyNeurips2020,
title = {Generative Tomography Reconstruction},
author = {Matteo Ronchetti and Davide Bacciu},
url = {https://arxiv.org/pdf/2010.14933.pdf, PDF},
year = {2020},
date = {2020-12-11},
booktitle = {34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Deep Learning and Inverse Problems},
abstract = {We propose an end-to-end differentiable architecture for tomography reconstruc-1tion that directly maps a noisy sinogram into a denoised reconstruction. Compared2to existing approaches our end-to-end architecture produces more accurate recon-3structions while using less parameters and time. We also propose a generative4model that, given a noisy sinogram, can sample realistic reconstructions. This5generative model can be used as prior inside an iterative process that, by tak-6ing into consideration the physical model, can reduce artifacts and errors in the7reconstructions.},
keywords = {adversarial learning, biomedical data, deep learning, generative model, inverse problems, machine vision},
pubstate = {published},
tppubtype = {workshop}
}
We propose an end-to-end differentiable architecture for tomography reconstruc-1tion that directly maps a noisy sinogram into a denoised reconstruction. Compared2to existing approaches our end-to-end architecture produces more accurate recon-3structions while using less parameters and time. We also propose a generative4model that, given a noisy sinogram, can sample realistic reconstructions. This5generative model can be used as prior inside an iterative process that, by tak-6ing into consideration the physical model, can reduce artifacts and errors in the7reconstructions. Bacciu, Davide; Conte, Alessio; Grossi, Roberto; Landolfi, Francesco; Marino, Andrea
K-plex Cover Pooling for Graph Neural Networks Workshop
34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Learning Meets Combinatorial Algorithms, 2020.
Abstract | BibTeX | Tags: deep learning, deep learning for graphs, graph data, graph pooling, structured data processing
@workshop{kplexWS2020,
title = {K-plex Cover Pooling for Graph Neural Networks},
author = {Davide Bacciu and Alessio Conte and Roberto Grossi and Francesco Landolfi and Andrea Marino},
year = {2020},
date = {2020-12-11},
booktitle = {34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Learning Meets Combinatorial Algorithms},
abstract = {We introduce a novel pooling technique which borrows from classical results in graph theory that is non-parametric and generalizes well to graphs of different nature and connectivity pattern. Our pooling method, named KPlexPool, builds on the concepts of graph covers and $k$-plexes, i.e. pseudo-cliques where each node can miss up to $k$ links. The experimental evaluation on molecular and social graph classification shows that KPlexPool achieves state of the art performances, supporting the intuition that well-founded graph-theoretic approaches can be effectively integrated in learning models for graphs. },
keywords = {deep learning, deep learning for graphs, graph data, graph pooling, structured data processing},
pubstate = {published},
tppubtype = {workshop}
}
We introduce a novel pooling technique which borrows from classical results in graph theory that is non-parametric and generalizes well to graphs of different nature and connectivity pattern. Our pooling method, named KPlexPool, builds on the concepts of graph covers and $k$-plexes, i.e. pseudo-cliques where each node can miss up to $k$ links. The experimental evaluation on molecular and social graph classification shows that KPlexPool achieves state of the art performances, supporting the intuition that well-founded graph-theoretic approaches can be effectively integrated in learning models for graphs. Bacciu, Davide; Numeroso, Danilo
Explaining Deep Graph Networks with Molecular Counterfactuals Workshop
34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Machine Learning for Molecules - Accepted as Contributed Talk (Oral), 2020.
Abstract | Links | BibTeX | Tags: deep learning for graphs, explainable AI, graph data, structured data processing
@workshop{megWS2020,
title = {Explaining Deep Graph Networks with Molecular Counterfactuals},
author = {Davide Bacciu and Danilo Numeroso},
url = {https://arxiv.org/pdf/2011.05134.pdf, Arxiv},
year = {2020},
date = {2020-12-11},
booktitle = {34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Machine Learning for Molecules - Accepted as Contributed Talk (Oral)},
abstract = {We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. We discuss preliminary results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighborhood of a molecule. },
keywords = {deep learning for graphs, explainable AI, graph data, structured data processing},
pubstate = {published},
tppubtype = {workshop}
}
We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. We discuss preliminary results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighborhood of a molecule. Carta, Antonio; Sperduti, Alessandro; Bacciu, Davide
Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization Workshop
34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Beyond BackPropagation: Novel Ideas for Training Neural Architectures, 2020.
Abstract | Links | BibTeX | Tags: deep learning, memory networks, recurrent neural network, Sequential data
@workshop{CartaNeuripsWS2020,
title = { Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization },
author = {Antonio Carta and Alessandro Sperduti and Davide Bacciu
},
url = {https://arxiv.org/abs/2011.02886, Arxiv},
year = {2020},
date = {2020-12-11},
booktitle = {34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Beyond BackPropagation: Novel Ideas for Training Neural Architectures},
abstract = {Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders for sequences, which allows to maximize the short-term memory and that can be solved with a closed-form solution without backpropagation. We introduce an initialization schema that pretrains the weights of a recurrent neural network to approximate the linear autoencoder of the input sequences and we show how such pretraining can better support solving hard classification tasks with long sequences. We test our approach on sequential and permuted MNIST. We show that the proposed approach achieves a much lower reconstruction error for long sequences and a better gradient propagation during the finetuning phase. },
keywords = {deep learning, memory networks, recurrent neural network, Sequential data},
pubstate = {published},
tppubtype = {workshop}
}
Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders for sequences, which allows to maximize the short-term memory and that can be solved with a closed-form solution without backpropagation. We introduce an initialization schema that pretrains the weights of a recurrent neural network to approximate the linear autoencoder of the input sequences and we show how such pretraining can better support solving hard classification tasks with long sequences. We test our approach on sequential and permuted MNIST. We show that the proposed approach achieves a much lower reconstruction error for long sequences and a better gradient propagation during the finetuning phase. Castellana, Daniele; Bacciu, Davide
Learning from Non-Binary Constituency Trees via Tensor Decomposition Conference
PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS (COLING 2020), 2020.
BibTeX | Tags: natural language processing, tensor factorization, tensor neural networks, tree structured data
@conference{CastellanaCOLING2020,
title = {Learning from Non-Binary Constituency Trees via Tensor Decomposition},
author = {Daniele Castellana and Davide Bacciu},
year = {2020},
date = {2020-12-08},
booktitle = {PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS (COLING 2020)},
keywords = {natural language processing, tensor factorization, tensor neural networks, tree structured data},
pubstate = {published},
tppubtype = {conference}
}
Valenti, Andrea; Barsotti, Michele; Brondi, Raffaello; Bacciu, Davide; Ascari, Luca
Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, 2020.
Abstract | Links | BibTeX | Tags: autoencoder, biomedical data, deep learning, Sequential data
@conference{smc2020,
title = {ROS-Neuro Integration of Deep Convolutional Autoencoders for EEG Signal Compression in Real-time BCIs},
author = {Andrea Valenti and Michele Barsotti and Raffaello Brondi and Davide Bacciu and Luca Ascari},
url = {https://arxiv.org/abs/2008.13485, Arxiv},
year = {2020},
date = {2020-10-11},
booktitle = {Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
publisher = {IEEE},
abstract = { Typical EEG-based BCI applications require the computation of complex functions over the noisy EEG channels to be carried out in an efficient way. Deep learning algorithms are capable of learning flexible nonlinear functions directly from data, and their constant processing latency is perfect for their deployment into online BCI systems. However, it is crucial for the jitter of the processing system to be as low as possible, in order to avoid unpredictable behaviour that can ruin the system's overall usability. In this paper, we present a novel encoding method, based on on deep convolutional autoencoders, that is able to perform efficient compression of the raw EEG inputs. We deploy our model in a ROS-Neuro node, thus making it suitable for the integration in ROS-based BCI and robotic systems in real world scenarios. The experimental results show that our system is capable to generate meaningful compressed encoding preserving to original information contained in the raw input. They also show that the ROS-Neuro node is able to produce such encodings at a steady rate, with minimal jitter. We believe that our system can represent an important step towards the development of an effective BCI processing pipeline fully standardized in ROS-Neuro framework. },
keywords = {autoencoder, biomedical data, deep learning, Sequential data},
pubstate = {published},
tppubtype = {conference}
}
Typical EEG-based BCI applications require the computation of complex functions over the noisy EEG channels to be carried out in an efficient way. Deep learning algorithms are capable of learning flexible nonlinear functions directly from data, and their constant processing latency is perfect for their deployment into online BCI systems. However, it is crucial for the jitter of the processing system to be as low as possible, in order to avoid unpredictable behaviour that can ruin the system's overall usability. In this paper, we present a novel encoding method, based on on deep convolutional autoencoders, that is able to perform efficient compression of the raw EEG inputs. We deploy our model in a ROS-Neuro node, thus making it suitable for the integration in ROS-based BCI and robotic systems in real world scenarios. The experimental results show that our system is capable to generate meaningful compressed encoding preserving to original information contained in the raw input. They also show that the ROS-Neuro node is able to produce such encodings at a steady rate, with minimal jitter. We believe that our system can represent an important step towards the development of an effective BCI processing pipeline fully standardized in ROS-Neuro framework. Bacciu, Davide; Errica, Federico; Micheli, Alessio; Podda, Marco
A Gentle Introduction to Deep Learning for Graphs Journal Article
In: Neural Networks, vol. 129, pp. 203-221, 2020.
Abstract | Links | BibTeX | Tags: deep learning, deep learning for graphs, graph data, structured data processing
@article{gentleGraphs2020,
title = {A Gentle Introduction to Deep Learning for Graphs},
author = {Davide Bacciu and Federico Errica and Alessio Micheli and Marco Podda},
url = {https://arxiv.org/abs/1912.12693, Arxiv
https://doi.org/10.1016/j.neunet.2020.06.006, Original Paper},
doi = {10.1016/j.neunet.2020.06.006},
year = {2020},
date = {2020-09-01},
journal = {Neural Networks},
volume = {129},
pages = {203-221},
publisher = {Elsevier},
abstract = {The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs. It favours a consistent and progressive introduction of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view to the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. It introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. The methodological exposition is complemented by a discussion of interesting research challenges and applications in the field. },
keywords = {deep learning, deep learning for graphs, graph data, structured data processing},
pubstate = {published},
tppubtype = {article}
}
The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs. It favours a consistent and progressive introduction of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view to the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. It introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. The methodological exposition is complemented by a discussion of interesting research challenges and applications in the field. Bacciu, Davide; Errica, Federico; Micheli, Alessio
Probabilistic Learning on Graphs via Contextual Architectures Journal Article
In: Journal of Machine Learning Research, vol. 21, no. 134, pp. 1−39, 2020.
Abstract | Links | BibTeX | Tags: deep learning, deep learning for graphs, graph data, hidden tree Markov model, structured data processing
@article{jmlrCGMM20,
title = {Probabilistic Learning on Graphs via Contextual Architectures},
author = {Davide Bacciu and Federico Errica and Alessio Micheli},
editor = {Pushmeet Kohli},
url = {http://jmlr.org/papers/v21/19-470.html, Paper},
year = {2020},
date = {2020-07-27},
journal = {Journal of Machine Learning Research},
volume = {21},
number = {134},
pages = {1−39},
abstract = {We propose a novel methodology for representation learning on graph-structured data, in which a stack of Bayesian Networks learns different distributions of a vertex's neighborhood. Through an incremental construction policy and layer-wise training, we can build deeper architectures with respect to typical graph convolutional neural networks, with benefits in terms of context spreading between vertices.
First, the model learns from graphs via maximum likelihood estimation without using target labels.
Then, a supervised readout is applied to the learned graph embeddings to deal with graph classification and vertex classification tasks, showing competitive results against neural models for graphs. The computational complexity is linear in the number of edges, facilitating learning on large scale data sets. By studying how depth affects the performances of our model, we discover that a broader context generally improves performances. In turn, this leads to a critical analysis of some benchmarks used in literature.},
keywords = {deep learning, deep learning for graphs, graph data, hidden tree Markov model, structured data processing},
pubstate = {published},
tppubtype = {article}
}
We propose a novel methodology for representation learning on graph-structured data, in which a stack of Bayesian Networks learns different distributions of a vertex's neighborhood. Through an incremental construction policy and layer-wise training, we can build deeper architectures with respect to typical graph convolutional neural networks, with benefits in terms of context spreading between vertices.
First, the model learns from graphs via maximum likelihood estimation without using target labels.
Then, a supervised readout is applied to the learned graph embeddings to deal with graph classification and vertex classification tasks, showing competitive results against neural models for graphs. The computational complexity is linear in the number of edges, facilitating learning on large scale data sets. By studying how depth affects the performances of our model, we discover that a broader context generally improves performances. In turn, this leads to a critical analysis of some benchmarks used in literature. Castellana, Daniele; Bacciu, Davide
Generalising Recursive Neural Models by Tensor Decomposition Conference
Proceedings of the 2020 IEEE World Congress on Computational Intelligence, 2020.
Links | BibTeX | Tags: deep learning, structured data processing, tensor factorization, tensor neural networks, tree structured data
@conference{Wcci20Tensor,
title = {Generalising Recursive Neural Models by Tensor Decomposition},
author = {Daniele Castellana and Davide Bacciu},
url = {https://arxiv.org/abs/2006.10021, Arxiv},
year = {2020},
date = {2020-07-19},
booktitle = {Proceedings of the 2020 IEEE World Congress on Computational Intelligence},
keywords = {deep learning, structured data processing, tensor factorization, tensor neural networks, tree structured data},
pubstate = {published},
tppubtype = {conference}
}
Cossu, Andrea; Carta, Antonio; Bacciu, Davide
Continual Learning with Gated Incremental Memories for Sequential Data Processing Conference
Proceedings of the 2020 IEEE World Congress on Computational Intelligence, 2020.
Links | BibTeX | Tags: Continual learning, deep learning, recurrent neural network, Sequential data
@conference{Wcci20CL,
title = {Continual Learning with Gated Incremental Memories for Sequential Data Processing},
author = {Andrea Cossu and Antonio Carta and Davide Bacciu},
url = {https://arxiv.org/pdf/2004.04077.pdf, Arxiv},
doi = {10.1109/IJCNN48605.2020.9207550},
year = {2020},
date = {2020-07-19},
booktitle = {Proceedings of the 2020 IEEE World Congress on Computational Intelligence},
keywords = {Continual learning, deep learning, recurrent neural network, Sequential data},
pubstate = {published},
tppubtype = {conference}
}
Valenti, Andrea; Carta, Antonio; Bacciu, Davide
Learning a Latent Space of Style-Aware Music Representations by Adversarial Autoencoders Conference
Proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020), 2020.
Links | BibTeX | Tags: artificial creativity, autoencoder, deep learning, generative model, music generation
@conference{ecai2020,
title = { Learning a Latent Space of Style-Aware Music Representations by Adversarial Autoencoders},
author = {Andrea Valenti and Antonio Carta and Davide Bacciu},
url = {https://arxiv.org/abs/2001.05494},
year = {2020},
date = {2020-06-08},
booktitle = {Proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020)},
keywords = {artificial creativity, autoencoder, deep learning, generative model, music generation},
pubstate = {published},
tppubtype = {conference}
}
Carta, Antonio; Sperduti, Alessandro; Bacciu, Davide
Incremental training of a recurrent neural network exploiting a multi-scale dynamic memory Conference
Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2020 (ECML-PKDD 2020), Springer International Publishing, 2020.
Abstract | BibTeX | Tags: autoencoder, deep learning, memory networks, recurrent neural network
@conference{ecml2020LMN,
title = {Incremental training of a recurrent neural network exploiting a multi-scale dynamic memory},
author = {Antonio Carta and Alessandro Sperduti and Davide Bacciu},
year = {2020},
date = {2020-06-05},
booktitle = {Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2020 (ECML-PKDD 2020)},
publisher = {Springer International Publishing},
abstract = {The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be introduced into a neural architecture by an appropriate modularization of the dynamic memory. In this paper we propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. First, we show how to extend the architecture of a simple RNN by separating its hidden state into different modules, each subsampling the network hidden activations at different frequencies. Then, we discuss a training algorithm where new modules are iteratively added to the model to learn progressively longer dependencies. Each new module works at a slower frequency than the previous ones and it is initialized to encode the subsampled sequence of hidden activations. Experimental results on synthetic and real-world datasets on speech recognition and handwritten characters show that the modular architecture and the incremental training algorithm improve the ability of recurrent neural networks to capture long-term dependencies.},
keywords = {autoencoder, deep learning, memory networks, recurrent neural network},
pubstate = {published},
tppubtype = {conference}
}
The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be introduced into a neural architecture by an appropriate modularization of the dynamic memory. In this paper we propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. First, we show how to extend the architecture of a simple RNN by separating its hidden state into different modules, each subsampling the network hidden activations at different frequencies. Then, we discuss a training algorithm where new modules are iteratively added to the model to learn progressively longer dependencies. Each new module works at a slower frequency than the previous ones and it is initialized to encode the subsampled sequence of hidden activations. Experimental results on synthetic and real-world datasets on speech recognition and handwritten characters show that the modular architecture and the incremental training algorithm improve the ability of recurrent neural networks to capture long-term dependencies.
Podda, Marco; Bacciu, Davide; Micheli, Alessio
A Deep Generative Model for Fragment-Based Molecule Generation Conference
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020) , 2020.
Abstract | Links | BibTeX | Tags: deep learning for graphs, generative model, graph data, molecule generation, recurrent neural network, structured data processing
@conference{aistats2020,
title = {A Deep Generative Model for Fragment-Based Molecule Generation},
author = {Marco Podda and Davide Bacciu and Alessio Micheli},
url = {https://arxiv.org/abs/2002.12826},
year = {2020},
date = {2020-06-03},
booktitle = {Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020) },
abstract = {Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative approaches addressing the challenge belong to two broad categories, differing in how molecules are represented. One approach encodes molecular graphs as strings of text, and learn their corresponding character-based language model. Another, more expressive, approach operates directly on the molecular graph. In this work, we address two limitations of the former: generation of invalid or duplicate molecules. To improve validity rates, we develop a language model for small molecular substructures called fragments, loosely inspired by the well-known paradigm of Fragment-Based Drug Design. In other words, we generate molecules fragment by fragment, instead of atom by atom. To improve uniqueness rates, we present a frequency-based clustering strategy that helps to generate molecules with infrequent fragments. We show experimentally that our model largely outperforms other language model-based competitors, reaching state-of-the-art performances typical of graph-based approaches. Moreover, generated molecules display molecular properties similar to those in the training sample, even in absence of explicit task-specific supervision.},
keywords = {deep learning for graphs, generative model, graph data, molecule generation, recurrent neural network, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative approaches addressing the challenge belong to two broad categories, differing in how molecules are represented. One approach encodes molecular graphs as strings of text, and learn their corresponding character-based language model. Another, more expressive, approach operates directly on the molecular graph. In this work, we address two limitations of the former: generation of invalid or duplicate molecules. To improve validity rates, we develop a language model for small molecular substructures called fragments, loosely inspired by the well-known paradigm of Fragment-Based Drug Design. In other words, we generate molecules fragment by fragment, instead of atom by atom. To improve uniqueness rates, we present a frequency-based clustering strategy that helps to generate molecules with infrequent fragments. We show experimentally that our model largely outperforms other language model-based competitors, reaching state-of-the-art performances typical of graph-based approaches. Moreover, generated molecules display molecular properties similar to those in the training sample, even in absence of explicit task-specific supervision.
Errica, Federico; Podda, Marco; Bacciu, Davide; Micheli, Alessio
A Fair Comparison of Graph Neural Networks for Graph Classification Conference
Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020), 2020.
Abstract | Links | BibTeX | Tags: deep learning, deep learning for graphs, graph data, structured data processing
@conference{iclr19,
title = {A Fair Comparison of Graph Neural Networks for Graph Classification},
author = {Federico Errica and Marco Podda and Davide Bacciu and Alessio Micheli},
url = {https://openreview.net/pdf?id=HygDF6NFPB, PDF
https://iclr.cc/virtual_2020/poster_HygDF6NFPB.html, Talk
https://github.com/diningphil/gnn-comparison, Code},
year = {2020},
date = {2020-04-30},
booktitle = {Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020)},
abstract = {Experimental reproducibility and replicability are critical topics in machine learning. Authors have often raised concerns about their lack in scientific publications to improve the quality of the field. Recently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works.
As such, several Graph Neural Network models have been developed to effectively tackle graph classification. However, experimental procedures often lack rigorousness and are hardly reproducible. Motivated by this, we provide an overview of common practices that should be avoided to fairly compare with the state of the art. To counter this troubling trend, we ran more than 47000 experiments in a controlled and uniform framework to re-evaluate five popular models across nine common benchmarks. Moreover, by comparing GNNs with structure-agnostic baselines we provide convincing evidence that, on some datasets, structural information has not been exploited yet. We believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.},
keywords = {deep learning, deep learning for graphs, graph data, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
Experimental reproducibility and replicability are critical topics in machine learning. Authors have often raised concerns about their lack in scientific publications to improve the quality of the field. Recently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works.
As such, several Graph Neural Network models have been developed to effectively tackle graph classification. However, experimental procedures often lack rigorousness and are hardly reproducible. Motivated by this, we provide an overview of common practices that should be avoided to fairly compare with the state of the art. To counter this troubling trend, we ran more than 47000 experiments in a controlled and uniform framework to re-evaluate five popular models across nine common benchmarks. Moreover, by comparing GNNs with structure-agnostic baselines we provide convincing evidence that, on some datasets, structural information has not been exploited yet. We believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.
Podda, Marco; Micheli, Alessio; Bacciu, Davide; Milazzo, Paolo
Biochemical Pathway Robustness Prediction with Graph Neural Networks Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20), 2020.
BibTeX | Tags: bioinformatics, biomedical data, deep learning for graphs, structured data processing
@conference{esann20Podda,
title = { Biochemical Pathway Robustness Prediction with Graph Neural Networks },
author = {Marco Podda and Alessio Micheli and Davide Bacciu and Paolo Milazzo},
editor = {Michel Verleysen},
year = {2020},
date = {2020-04-21},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20)},
keywords = {bioinformatics, biomedical data, deep learning for graphs, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
Errica, Federico; Bacciu, Davide; Micheli, Alessio
Theoretically Expressive and Edge-aware Graph Learning Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20), 2020.
Abstract | Links | BibTeX | Tags: deep learning for graphs, structured data processing
@conference{esann20Errica,
title = { Theoretically Expressive and Edge-aware Graph Learning },
author = {Federico Errica and Davide Bacciu and Alessio Micheli},
editor = {Michel Verleysen},
url = {https://arxiv.org/abs/2001.09005},
year = {2020},
date = {2020-04-21},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20)},
abstract = {We propose a new Graph Neural Network that combines recent advancements in the field. We give theoretical contributions by proving that the model is strictly more general than the Graph Isomorphism Network and the Gated Graph Neural Network, as it can approximate the same functions and deal with arbitrary edge values. Then, we show how a single node information can flow through the graph unchanged. },
keywords = {deep learning for graphs, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
We propose a new Graph Neural Network that combines recent advancements in the field. We give theoretical contributions by proving that the model is strictly more general than the Graph Isomorphism Network and the Gated Graph Neural Network, as it can approximate the same functions and deal with arbitrary edge values. Then, we show how a single node information can flow through the graph unchanged. Crecchi, Francesco; de Bodt, Cyril; Bacciu, Davide; Verleysen, Michel; John, Lee
Perplexity-free Parametric t-SNE Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20), 2020.
BibTeX | Tags: data visualization, manifold learning, neural networks, unsupervised learning
@conference{esann20Crecchi,
title = { Perplexity-free Parametric t-SNE},
author = {Francesco Crecchi and Cyril de Bodt and Davide Bacciu and Michel Verleysen and Lee John},
editor = {Michel Verleysen},
year = {2020},
date = {2020-04-21},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20)},
keywords = {data visualization, manifold learning, neural networks, unsupervised learning},
pubstate = {published},
tppubtype = {conference}
}
Bacciu, Davide; Mandic, Danilo
Tensor Decompositions in Deep Learning Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20), 2020.
Links | BibTeX | Tags: deep learning, structured data processing, tensor factorization
@conference{esann20Tutorial,
title = {Tensor Decompositions in Deep Learning},
author = {Davide Bacciu and Danilo Mandic},
editor = {Michel Verleysen},
url = {https://arxiv.org/abs/2002.11835},
year = {2020},
date = {2020-04-21},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20)},
keywords = {deep learning, structured data processing, tensor factorization},
pubstate = {published},
tppubtype = {conference}
}
Castellana, Daniele; Bacciu, Davide
Tensor Decompositions in Recursive Neural Networks for Tree-Structured Data Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20), 2020.
Links | BibTeX | Tags: deep learning, structured data processing, tensor factorization, tree structured data
@conference{esann20Castellana,
title = { Tensor Decompositions in Recursive Neural Networks for Tree-Structured Data },
author = {Daniele Castellana and Davide Bacciu},
editor = {Michel Verleysen},
url = {https://arxiv.org/pdf/2006.10619.pdf, Arxiv},
year = {2020},
date = {2020-04-21},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20)},
keywords = {deep learning, structured data processing, tensor factorization, tree structured data},
pubstate = {published},
tppubtype = {conference}
}
Bacciu, Davide; Micheli, Alessio
Deep Learning for Graphs Book Chapter
In: Oneto, Luca; Navarin, Nicolo; Sperduti, Alessandro; Anguita, Davide (Ed.): Recent Trends in Learning From Data: Tutorials from the INNS Big Data and Deep Learning Conference (INNSBDDL2019), vol. 896, pp. 99-127, Springer International Publishing, 2020, ISBN: 978-3-030-43883-8.
Abstract | Links | BibTeX | Tags: deep learning for graphs, generative model, graph data, molecule generation, recurrent neural network, structured data processing
@inbook{graphsBDDL2020,
title = {Deep Learning for Graphs},
author = {Davide Bacciu and Alessio Micheli},
editor = {Luca Oneto and Nicolo Navarin and Alessandro Sperduti and Davide Anguita
},
url = {https://link.springer.com/chapter/10.1007/978-3-030-43883-8_5},
doi = {10.1007/978-3-030-43883-8_5},
isbn = {978-3-030-43883-8},
year = {2020},
date = {2020-04-04},
booktitle = {Recent Trends in Learning From Data: Tutorials from the INNS Big Data and Deep Learning Conference (INNSBDDL2019)},
volume = {896},
pages = {99-127},
publisher = {Springer International Publishing},
series = {Studies in Computational Intelligence Series},
abstract = {We introduce an overview of methods for learning in structured domains covering foundational works developed within the last twenty years to deal with a whole range of complex data representations, including hierarchical structures, graphs and networks, and giving special attention to recent deep learning models for graphs. While we provide a general introduction to the field, we explicitly focus on the neural network paradigm showing how, across the years, these models have been extended to the adaptive processing of incrementally more complex classes of structured data. The ultimate aim is to show how to cope with the fundamental issue of learning adaptive representations for samples with varying size and topology.},
keywords = {deep learning for graphs, generative model, graph data, molecule generation, recurrent neural network, structured data processing},
pubstate = {published},
tppubtype = {inbook}
}
We introduce an overview of methods for learning in structured domains covering foundational works developed within the last twenty years to deal with a whole range of complex data representations, including hierarchical structures, graphs and networks, and giving special attention to recent deep learning models for graphs. While we provide a general introduction to the field, we explicitly focus on the neural network paradigm showing how, across the years, these models have been extended to the adaptive processing of incrementally more complex classes of structured data. The ultimate aim is to show how to cope with the fundamental issue of learning adaptive representations for samples with varying size and topology.
Ferrari, Elisa; Retico, Alessandra; Bacciu, Davide
Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI) Journal Article
In: Artificial Intelligence in Medicine, vol. 103, 2020.
Abstract | Links | BibTeX | Tags: artificial intelligence, bioinformatics, biomedical data, explainable AI, statistics
@article{aime20Confound,
title = {Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI)},
author = {Elisa Ferrari and Alessandra Retico and Davide Bacciu},
url = {https://arxiv.org/abs/1905.08871},
doi = {10.1016/j.artmed.2020.101804},
year = {2020},
date = {2020-03-01},
journal = {Artificial Intelligence in Medicine},
volume = {103},
abstract = {Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the confounders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data. },
keywords = {artificial intelligence, bioinformatics, biomedical data, explainable AI, statistics},
pubstate = {published},
tppubtype = {article}
}
Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the confounders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data. 2019
Bacciu, Davide; Micheli, Alessio; Podda, Marco
Edge-based sequential graph generation with recurrent neural networks Journal Article
In: Neurocomputing, 2019.
Abstract | Links | BibTeX | Tags: deep learning for graphs, generative model, graph data, structured data processing
@article{neucompEsann19,
title = {Edge-based sequential graph generation with recurrent neural networks},
author = {Davide Bacciu and Alessio Micheli and Marco Podda},
url = {https://arxiv.org/abs/2002.00102v1},
year = {2019},
date = {2019-12-31},
journal = {Neurocomputing},
abstract = { Graph generation with Machine Learning is an open problem with applications in various research fields. In this work, we propose to cast the generative process of a graph into a sequential one, relying on a node ordering procedure. We use this sequential process to design a novel generative model composed of two recurrent neural networks that learn to predict the edges of graphs: the first network generates one endpoint of each edge, while the second network generates the other endpoint conditioned on the state of the first. We test our approach extensively on five different datasets, comparing with two well-known baselines coming from graph literature, and two recurrent approaches, one of which holds state of the art performances. Evaluation is conducted considering quantitative and qualitative characteristics of the generated samples. Results show that our approach is able to yield novel, and unique graphs originating from very different distributions, while retaining structural properties very similar to those in the training sample. Under the proposed evaluation framework, our approach is able to reach performances comparable to the current state of the art on the graph generation task. },
keywords = {deep learning for graphs, generative model, graph data, structured data processing},
pubstate = {published},
tppubtype = {article}
}
Graph generation with Machine Learning is an open problem with applications in various research fields. In this work, we propose to cast the generative process of a graph into a sequential one, relying on a node ordering procedure. We use this sequential process to design a novel generative model composed of two recurrent neural networks that learn to predict the edges of graphs: the first network generates one endpoint of each edge, while the second network generates the other endpoint conditioned on the state of the first. We test our approach extensively on five different datasets, comparing with two well-known baselines coming from graph literature, and two recurrent approaches, one of which holds state of the art performances. Evaluation is conducted considering quantitative and qualitative characteristics of the generated samples. Results show that our approach is able to yield novel, and unique graphs originating from very different distributions, while retaining structural properties very similar to those in the training sample. Under the proposed evaluation framework, our approach is able to reach performances comparable to the current state of the art on the graph generation task. 
Bacciu, Davide; Carta, Antonio
Sequential Sentence Embeddings for Semantic Similarity Conference
Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI'19), IEEE, 2019.
Abstract | Links | BibTeX | Tags: autoencoder, deep learning, memory networks, natural language, recurrent neural network
@conference{ssci19,
title = {Sequential Sentence Embeddings for Semantic Similarity},
author = {Davide Bacciu and Antonio Carta},
doi = {10.1109/SSCI44817.2019.9002824},
year = {2019},
date = {2019-12-06},
booktitle = {Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI'19)},
publisher = {IEEE},
abstract = { Sentence embeddings are distributed representations of sentences intended to be general features to be effectively used as input for deep learning models across different natural language processing tasks.
State-of-the-art sentence embeddings for semantic similarity are computed with a weighted average of pretrained word embeddings, hence completely ignoring the contribution of word ordering within a sentence in defining its semantics. We propose a novel approach to compute sentence embeddings for semantic similarity that exploits a linear autoencoder for sequences. The method can be trained in closed form and it is easy to fit on unlabeled sentences. Our method provides a grounded approach to identify and subtract common discourse from a sentence and its embedding, to remove associated uninformative features. Unlike similar methods in the literature (e.g. the popular Smooth Inverse Frequency approach), our method is able to account for word order. We show that our estimate of the common discourse vector improves the results on two different semantic similarity benchmarks when compared to related approaches from the literature.},
keywords = {autoencoder, deep learning, memory networks, natural language, recurrent neural network},
pubstate = {published},
tppubtype = {conference}
}
Sentence embeddings are distributed representations of sentences intended to be general features to be effectively used as input for deep learning models across different natural language processing tasks.
State-of-the-art sentence embeddings for semantic similarity are computed with a weighted average of pretrained word embeddings, hence completely ignoring the contribution of word ordering within a sentence in defining its semantics. We propose a novel approach to compute sentence embeddings for semantic similarity that exploits a linear autoencoder for sequences. The method can be trained in closed form and it is easy to fit on unlabeled sentences. Our method provides a grounded approach to identify and subtract common discourse from a sentence and its embedding, to remove associated uninformative features. Unlike similar methods in the literature (e.g. the popular Smooth Inverse Frequency approach), our method is able to account for word order. We show that our estimate of the common discourse vector improves the results on two different semantic similarity benchmarks when compared to related approaches from the literature.
Bacciu, Davide
Reti neurali e linguaggio. Le insidie nascoste di un'algebra delle parole Online
Tavosanis, Mirko (Ed.): Lingua Italiana - Treccani 2019.
Links | BibTeX | Tags: artificial intelligence, natural language processing, neural networks
@online{treccani19,
title = {Reti neurali e linguaggio. Le insidie nascoste di un'algebra delle parole},
author = {Davide Bacciu},
editor = {Mirko Tavosanis},
url = {http://www.treccani.it/magazine/lingua_italiana/speciali/IA/02_Bacciu.html},
year = {2019},
date = {2019-12-03},
organization = {Lingua Italiana - Treccani},
keywords = {artificial intelligence, natural language processing, neural networks},
pubstate = {published},
tppubtype = {online}
}
Bacciu, Davide; Sotto, Luigi Di
A non-negative factorization approach to node pooling in graph convolutional neural networks Conference
Proceedings of the 18th International Conference of the Italian Association for Artificial Intelligence (AIIA 2019), Lecture Notes in Artificial Intelligence Springer-Verlag, 2019.
Links | BibTeX | Tags: deep learning, deep learning for graphs, graph data, hidden tree Markov model, structured data processing
@conference{aiia2019,
title = {A non-negative factorization approach to node pooling in graph convolutional neural networks},
author = {Davide Bacciu and Luigi {Di Sotto}},
url = {https://arxiv.org/pdf/1909.03287.pdf},
year = {2019},
date = {2019-11-22},
booktitle = {Proceedings of the 18th International Conference of the Italian Association for Artificial Intelligence (AIIA 2019)},
publisher = {Springer-Verlag},
series = {Lecture Notes in Artificial Intelligence},
keywords = {deep learning, deep learning for graphs, graph data, hidden tree Markov model, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
Cafagna, Michele; Mattei, Lorenzo De; Bacciu, Davide; Nissim, Malvina
Suitable doesn’t mean attractive. Human-based evaluation of automatically generated headlines Conference
Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it 2019), vol. 2481 , AI*IA series CEUR, 2019.
Abstract | Links | BibTeX | Tags: natural language, recurrent neural network, text generation
@conference{clic2019,
title = {Suitable doesn’t mean attractive. Human-based evaluation of automatically generated headlines},
author = {Michele Cafagna and Lorenzo {De Mattei} and Davide Bacciu and Malvina Nissim},
editor = {Raffaella Bernardi and Roberto Navigli and Giovanni Semeraro},
url = {http://ceur-ws.org/Vol-2481/paper13.pdf},
year = {2019},
date = {2019-11-15},
booktitle = {Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it 2019)},
volume = {2481 },
publisher = {CEUR},
series = {AI*IA series},
abstract = {We train three different models to generate newspaper headlines from a portion of the corresponding article. The articles are obtained from two mainstream Italian newspapers. In order to assess the models’ performance, we set up a human-based evaluation where 30 different native speakers expressed their judgment over a variety of aspects. The outcome shows that (i) pointer networks perform better than standard sequence to sequence models, creating mostly correct and appropriate titles; (ii) the suitability of a headline to its article for pointer networks is on par or better than the gold headline; (iii) gold headlines are still by far more inviting than generated headlines to read the whole article, highlighting the contrast between human creativity and content appropriateness.},
keywords = {natural language, recurrent neural network, text generation},
pubstate = {published},
tppubtype = {conference}
}
We train three different models to generate newspaper headlines from a portion of the corresponding article. The articles are obtained from two mainstream Italian newspapers. In order to assess the models’ performance, we set up a human-based evaluation where 30 different native speakers expressed their judgment over a variety of aspects. The outcome shows that (i) pointer networks perform better than standard sequence to sequence models, creating mostly correct and appropriate titles; (ii) the suitability of a headline to its article for pointer networks is on par or better than the gold headline; (iii) gold headlines are still by far more inviting than generated headlines to read the whole article, highlighting the contrast between human creativity and content appropriateness. Bacciu, Davide; Carta, Antonio; Sperduti, Alessandro
Linear Memory Networks Conference
Proceedings of the 28th International Conference on Artificial Neural Networks (ICANN 2019), , vol. 11727, Lecture Notes in Computer Science Springer-Verlag, 2019.
Abstract | Links | BibTeX | Tags: autoencoder, deep learning, memory networks, recurrent neural network
@conference{lmnArx18,
title = {Linear Memory Networks},
author = {Davide Bacciu and Antonio Carta and Alessandro Sperduti},
url = {https://arxiv.org/pdf/1811.03356.pdf},
doi = {10.1007/978-3-030-30487-4_40},
year = {2019},
date = {2019-09-17},
booktitle = {Proceedings of the 28th International Conference on Artificial Neural Networks (ICANN 2019), },
volume = {11727},
pages = {513-525 },
publisher = {Springer-Verlag},
series = {Lecture Notes in Computer Science},
abstract = {Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled. We introduce a novel recurrent architecture based on the conceptual separation between the functional input-output transformation and the memory mechanism, showing how they can be implemented through different neural components. By building on such conceptualization, we introduce the Linear Memory Network, a recurrent model comprising a feedforward neural network, realizing the non-linear functional transformation, and a linear autoencoder for sequences, implementing the memory component. The resulting architecture can be efficiently trained by building on closed-form solutions to linear optimization problems. Further, by exploiting equivalence results between feedforward and recurrent neural networks we devise a pretraining schema for the proposed architecture. Experiments on polyphonic music datasets show competitive results against gated recurrent networks and other state of the art models. },
keywords = {autoencoder, deep learning, memory networks, recurrent neural network},
pubstate = {published},
tppubtype = {conference}
}
Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled. We introduce a novel recurrent architecture based on the conceptual separation between the functional input-output transformation and the memory mechanism, showing how they can be implemented through different neural components. By building on such conceptualization, we introduce the Linear Memory Network, a recurrent model comprising a feedforward neural network, realizing the non-linear functional transformation, and a linear autoencoder for sequences, implementing the memory component. The resulting architecture can be efficiently trained by building on closed-form solutions to linear optimization problems. Further, by exploiting equivalence results between feedforward and recurrent neural networks we devise a pretraining schema for the proposed architecture. Experiments on polyphonic music datasets show competitive results against gated recurrent networks and other state of the art models. Cosimo, Della Santina; Giuseppe, Averta; Visar, Arapi; Alessandro, Settimi; Giuseppe, Catalano Manuel; Davide, Bacciu; Antonio, Bicchi; Matteo, Bianchi
Autonomous Grasping with SoftHands: Combining Human Inspiration, Deep Learning and Embodied Machine Intelligence Presentation
11.09.2019.
BibTeX | Tags: deep learning, robotics
@misc{automatica2019,
title = {Autonomous Grasping with SoftHands: Combining Human Inspiration, Deep Learning and Embodied Machine Intelligence},
author = {Della Santina Cosimo and Averta Giuseppe and Arapi Visar and Settimi Alessandro and Catalano Manuel Giuseppe and Bacciu Davide and Bicchi Antonio and Bianchi Matteo},
year = {2019},
date = {2019-09-11},
booktitle = {Oral contribution to AUTOMATICA.IT 2019 },
keywords = {deep learning, robotics},
pubstate = {published},
tppubtype = {presentation}
}
Davide, Bacciu; Maurizio, Di Rocco; Mauro, Dragone; Claudio, Gallicchio; Alessio, Micheli; Alessandro, Saffiotti
An Ambient Intelligence Approach for Learning in Smart Robotic Environments Journal Article
In: Computational Intelligence, 2019, (Early View (Online Version of Record before inclusion in an issue)
).
Abstract | Links | BibTeX | Tags: ambient assisted living, Echo state networks, feature selection, multivariate time-series, pervasive computing, planning, recurrent neural network, reservoir computing, robotic ecology, wireless sensor networks
@article{rubicon2019CI,
title = {An Ambient Intelligence Approach for Learning in Smart Robotic Environments},
author = {Bacciu Davide and Di Rocco Maurizio and Dragone Mauro and Gallicchio Claudio and Micheli Alessio and Saffiotti Alessandro},
doi = {10.1111/coin.12233},
year = {2019},
date = {2019-07-31},
journal = {Computational Intelligence},
abstract = {Smart robotic environments combine traditional (ambient) sensing devices and mobile robots. This combination extends the type of applications that can be considered, reduces their complexity, and enhances the individual values of the devices involved by enabling new services that cannot be performed by a single device. In order to reduce the amount of preparation and pre-programming required for their deployment in real world applications, it is important to make these systems self-learning, self-configuring, and self-adapting. The solution presented in this paper is based upon a type of compositional adaptation where (possibly multiple) plans of actions are created through planning and involve the activation of pre-existing capabilities. All the devices in the smart environment participate in a pervasive learning infrastructure, which is exploited to recognize which plans of actions are most suited to the current situation. The system is evaluated in experiments run in a real domestic environment, showing its ability to pro-actively and smoothly adapt to subtle changes in the environment and in the habits and preferences
of their user(s).},
note = {Early View (Online Version of Record before inclusion in an issue)
},
keywords = {ambient assisted living, Echo state networks, feature selection, multivariate time-series, pervasive computing, planning, recurrent neural network, reservoir computing, robotic ecology, wireless sensor networks},
pubstate = {published},
tppubtype = {article}
}
Smart robotic environments combine traditional (ambient) sensing devices and mobile robots. This combination extends the type of applications that can be considered, reduces their complexity, and enhances the individual values of the devices involved by enabling new services that cannot be performed by a single device. In order to reduce the amount of preparation and pre-programming required for their deployment in real world applications, it is important to make these systems self-learning, self-configuring, and self-adapting. The solution presented in this paper is based upon a type of compositional adaptation where (possibly multiple) plans of actions are created through planning and involve the activation of pre-existing capabilities. All the devices in the smart environment participate in a pervasive learning infrastructure, which is exploited to recognize which plans of actions are most suited to the current situation. The system is evaluated in experiments run in a real domestic environment, showing its ability to pro-actively and smoothly adapt to subtle changes in the environment and in the habits and preferences
of their user(s). Castellana, Daniele; Bacciu, Davide
Bayesian Tensor Factorisation for Bottom-up Hidden Tree Markov Models Conference
Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN 2019I) , IEEE, 2019.
Abstract | Links | BibTeX | Tags: graphical models, hidden tree Markov model, structured data processing, tree structured data; tensor factorization; Bayesian learning
@conference{ijcnn2019,
title = {Bayesian Tensor Factorisation for Bottom-up Hidden Tree Markov Models},
author = {Daniele Castellana and Davide Bacciu},
url = {https://arxiv.org/pdf/1905.13528.pdf},
year = {2019},
date = {2019-07-15},
booktitle = {Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN 2019I) },
publisher = {IEEE},
abstract = {Bottom-Up Hidden Tree Markov Model is a highly expressive model for tree-structured data. Unfortunately, it cannot be used in practice due to the intractable size of its state-transition matrix. We propose a new approximation which lies on the Tucker factorisation of tensors. The probabilistic interpretation of such approximation allows us to define a new probabilistic model for tree-structured data. Hence, we define the new approximated model and we derive its learning algorithm. Then, we empirically assess the effective power of the new model evaluating it on two different tasks. In both cases, our model outperforms the other approximated model known in the literature.},
keywords = {graphical models, hidden tree Markov model, structured data processing, tree structured data; tensor factorization; Bayesian learning},
pubstate = {published},
tppubtype = {conference}
}
Bottom-Up Hidden Tree Markov Model is a highly expressive model for tree-structured data. Unfortunately, it cannot be used in practice due to the intractable size of its state-transition matrix. We propose a new approximation which lies on the Tucker factorisation of tensors. The probabilistic interpretation of such approximation allows us to define a new probabilistic model for tree-structured data. Hence, we define the new approximated model and we derive its learning algorithm. Then, we empirically assess the effective power of the new model evaluating it on two different tasks. In both cases, our model outperforms the other approximated model known in the literature. Davide, Bacciu; Daniele, Castellana
Bayesian Mixtures of Hidden Tree Markov Models for Structured Data Clustering Journal Article
In: Neurocomputing, vol. 342, pp. 49-59, 2019, ISBN: 0925-2312.
Abstract | Links | BibTeX | Tags: graphical models, hidden tree Markov model, structured data processing, tree structured data, unsupervised learning
@article{neucomBayesHTMM,
title = {Bayesian Mixtures of Hidden Tree Markov Models for Structured Data Clustering},
author = {Bacciu Davide and Castellana Daniele},
url = {https://doi.org/10.1016/j.neucom.2018.11.091},
doi = {10.1016/j.neucom.2018.11.091},
isbn = {0925-2312},
year = {2019},
date = {2019-05-21},
journal = {Neurocomputing},
volume = {342},
pages = {49-59},
abstract = {The paper deals with the problem of unsupervised learning with structured data, proposing a mixture model approach to cluster tree samples. First, we discuss how to use the Switching-Parent Hidden Tree Markov Model, a compositional model for learning tree distributions, to define a finite mixture model where the number of components is fixed by a hyperparameter. Then, we show how to relax such an assumption by introducing a Bayesian non-parametric mixture model where the number of necessary hidden tree components is learned from data. Experimental validation on synthetic and real datasets show the benefit of mixture models over simple hidden tree models in clustering applications. Further, we provide a characterization of the behaviour of the two mixture models for different choices of their hyperparameters.},
keywords = {graphical models, hidden tree Markov model, structured data processing, tree structured data, unsupervised learning},
pubstate = {published},
tppubtype = {article}
}
The paper deals with the problem of unsupervised learning with structured data, proposing a mixture model approach to cluster tree samples. First, we discuss how to use the Switching-Parent Hidden Tree Markov Model, a compositional model for learning tree distributions, to define a finite mixture model where the number of components is fixed by a hyperparameter. Then, we show how to relax such an assumption by introducing a Bayesian non-parametric mixture model where the number of necessary hidden tree components is learned from data. Experimental validation on synthetic and real datasets show the benefit of mixture models over simple hidden tree models in clustering applications. Further, we provide a characterization of the behaviour of the two mixture models for different choices of their hyperparameters.
Crecchi, Francesco; Bacciu, Davide; Biggio, Battista
Detecting Black-box Adversarial Examples through Nonlinear Dimensionality Reduction Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'19), i6doc.com, Louvain-la-Neuve, Belgium, 2019.
Links | BibTeX | Tags: adversarial attacks, deep learning, manifold learning
@conference{esann19Attacks,
title = {Detecting Black-box Adversarial Examples through Nonlinear Dimensionality Reduction},
author = {Francesco Crecchi and Davide Bacciu and Battista Biggio },
editor = {Michel Verleysen},
url = {https://arxiv.org/pdf/1904.13094.pdf},
year = {2019},
date = {2019-04-24},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'19)},
publisher = {i6doc.com},
address = {Louvain-la-Neuve, Belgium},
keywords = {adversarial attacks, deep learning, manifold learning},
pubstate = {published},
tppubtype = {conference}
}
Bacciu, Davide; Micheli, Alessio; Podda, Marco
Graph generation by sequential edge prediction Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'19), i6doc.com, Louvain-la-Neuve, Belgium, 2019.
Links | BibTeX | Tags: deep learning for graphs, generative model, graph data, structured data processing
@conference{esann19GraphGen,
title = {Graph generation by sequential edge prediction},
author = {Davide Bacciu and Alessio Micheli and Marco Podda},
editor = {Michel Verleysen},
url = {https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-107.pdf},
year = {2019},
date = {2019-04-24},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'19)},
publisher = {i6doc.com},
address = {Louvain-la-Neuve, Belgium},
keywords = {deep learning for graphs, generative model, graph data, structured data processing},
pubstate = {published},
tppubtype = {conference}
}
Bacciu, Davide; Biggio, Battista; Crecchi, Francesco; Lisboa, Paulo J. G.; Martin, José D.; Oneto, Luca; Vellido, Alfredo
Societal Issues in Machine Learning: When Learning from Data is Not Enough Conference
Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'19), i6doc.com, Louvain-la-Neuve, Belgium, 2019.
Links | BibTeX | Tags: adversarial attacks, deep learning, explainable AI
@conference{esann19Tutorial,
title = {Societal Issues in Machine Learning: When Learning from Data is Not Enough},
author = { Davide Bacciu and Battista Biggio and Francesco Crecchi and Paulo J. G. Lisboa and José D. Martin and Luca Oneto and Alfredo Vellido},
editor = {Michel Verleysen},
url = {https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-6.pdf},
year = {2019},
date = {2019-04-24},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'19)},
publisher = {i6doc.com},
address = {Louvain-la-Neuve, Belgium},
keywords = {adversarial attacks, deep learning, explainable AI},
pubstate = {published},
tppubtype = {conference}
}
Bacciu, Davide; Crecchi, Francesco
Augmenting Recurrent Neural Networks Resilience by Dropout Journal Article
In: IEEE Transactions on Neural Networs and Learning Systems, 2019.
Abstract | Links | BibTeX | Tags: ambient assisted living, deep learning, Echo state networks, recurrent neural network, reservoir computing
@article{tnnnls_dropin2019,
title = {Augmenting Recurrent Neural Networks Resilience by Dropout},
author = {Davide Bacciu and Francesco Crecchi },
doi = {10.1109/TNNLS.2019.2899744},
year = {2019},
date = {2019-03-31},
journal = {IEEE Transactions on Neural Networs and Learning Systems},
abstract = {The paper discusses the simple idea that dropout regularization can be used to efficiently induce resiliency to missing inputs at prediction time in a generic neural network. We show how the approach can be effective on tasks where imputation strategies often fail, namely involving recurrent neural networks and scenarios where whole sequences of input observations are missing. The experimental analysis provides an assessment of the accuracy-resiliency tradeoff in multiple recurrent models, including reservoir computing methods, and comprising real-world ambient intelligence and biomedical time series.},
keywords = {ambient assisted living, deep learning, Echo state networks, recurrent neural network, reservoir computing},
pubstate = {published},
tppubtype = {article}
}
The paper discusses the simple idea that dropout regularization can be used to efficiently induce resiliency to missing inputs at prediction time in a generic neural network. We show how the approach can be effective on tasks where imputation strategies often fail, namely involving recurrent neural networks and scenarios where whole sequences of input observations are missing. The experimental analysis provides an assessment of the accuracy-resiliency tradeoff in multiple recurrent models, including reservoir computing methods, and comprising real-world ambient intelligence and biomedical time series.
Cosimo, Della Santina; Visar, Arapi; Giuseppe, Averta; Francesca, Damiani; Gaia, Fiore; Alessandro, Settimi; Giuseppe, Catalano Manuel; Davide, Bacciu; Antonio, Bicchi; Matteo, Bianchi
Learning from humans how to grasp: a data-driven architecture for autonomous grasping with anthropomorphic soft hands Journal Article
In: IEEE Robotics and Automation Letters, pp. 1-8, 2019, ISSN: 2377-3766, (Also accepted for presentation at ICRA 2019).
Links | BibTeX | Tags: convolutional neural network, deep learning, image understanding, machine vision, recurrent neural network, robotics
@article{ral2019,
title = {Learning from humans how to grasp: a data-driven architecture for autonomous grasping with anthropomorphic soft hands},
author = {Della Santina Cosimo and Arapi Visar and Averta Giuseppe and Damiani Francesca and Fiore Gaia and Settimi Alessandro and Catalano Manuel Giuseppe and Bacciu Davide and Bicchi Antonio and Bianchi Matteo},
url = {https://ieeexplore.ieee.org/document/8629968},
doi = {10.1109/LRA.2019.2896485},
issn = {2377-3766},
year = {2019},
date = {2019-02-01},
journal = {IEEE Robotics and Automation Letters},
pages = {1-8},
note = {Also accepted for presentation at ICRA 2019},
keywords = {convolutional neural network, deep learning, image understanding, machine vision, recurrent neural network, robotics},
pubstate = {published},
tppubtype = {article}
}
Davide, Bacciu; Antonio, Bruno
Deep Tree Transductions - A Short Survey Conference
Proceedings of the 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) , Recent Advances in Big Data and Deep Learning Springer International Publishing, 2019.
Abstract | Links | BibTeX | Tags: deep learning, recurrent neural network, structured data processing, tree structured data
@conference{inns2019,
title = {Deep Tree Transductions - A Short Survey},
author = {Bacciu Davide and Bruno Antonio},
editor = {Luca Oneto and Nicol{`o} Navarin and Alessandro Sperduti and Davide Anguita},
url = {https://arxiv.org/abs/1902.01737},
doi = {10.1007/978-3-030-16841-4_25},
year = {2019},
date = {2019-01-04},
booktitle = {Proceedings of the 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) },
pages = {236--245},
publisher = {Springer International Publishing},
series = {Recent Advances in Big Data and Deep Learning},
abstract = {The paper surveys recent extensions of the Long-Short Term Memory networks to handle tree structures from the perspective of learning non-trivial forms of isomorph structured transductions. It provides a discussion of modern TreeLSTM models, showing the effect of the bias induced by the direction of tree processing. An empirical analysis is performed on real-world benchmarks, highlighting how there is no single model adequate to effectively approach all transduction problems.},
keywords = {deep learning, recurrent neural network, structured data processing, tree structured data},
pubstate = {published},
tppubtype = {conference}
}
The paper surveys recent extensions of the Long-Short Term Memory networks to handle tree structures from the perspective of learning non-trivial forms of isomorph structured transductions. It provides a discussion of modern TreeLSTM models, showing the effect of the bias induced by the direction of tree processing. An empirical analysis is performed on real-world benchmarks, highlighting how there is no single model adequate to effectively approach all transduction problems.2018
Arapi, Visar; Santina, Cosimo Della; Bacciu, Davide; Bianchi, Matteo; Bicchi, Antonio
DeepDynamicHand: A deep neural architecture for labeling hand manipulation strategies in video sources exploiting temporal information Journal Article
In: Frontiers in Neurorobotics, vol. 12, pp. 86, 2018.
Abstract | Links | BibTeX | Tags: convolutional neural network, deep learning, image understanding, machine vision, recurrent neural network, robotics
@article{frontNeurob18,
title = {DeepDynamicHand: A deep neural architecture for labeling hand manipulation strategies in video sources exploiting temporal information },
author = {Visar Arapi and Cosimo Della Santina and Davide Bacciu and Matteo Bianchi and Antonio Bicchi},
url = {https://www.frontiersin.org/articles/10.3389/fnbot.2018.00086/full},
doi = {10.3389/fnbot.2018.00086},
year = {2018},
date = {2018-12-17},
journal = {Frontiers in Neurorobotics},
volume = {12},
pages = {86},
abstract = {Humans are capable of complex manipulation interactions with the environment, relying on the intrinsic adaptability and compliance of their hands. Recently, soft robotic manipulation has attempted to reproduce such an extraordinary behavior, through the design of deformable yet robust end-effectors. To this goal, the investigation of human behavior has become crucial to correctly inform technological developments of robotic hands that can successfully exploit environmental constraint as humans actually do. Among the different tools robotics can leverage on to achieve this objective, deep learning has emerged as a promising approach for the study and then the implementation of neuro-scientific observations on the artificial side. However, current approaches tend to neglect the dynamic nature of hand pose recognition problems, limiting the effectiveness of these techniques in identifying sequences of manipulation primitives underpinning action generation, e.g. during purposeful interaction with the environment. In this work, we propose a vision-based supervised Hand Pose Recognition method which, for the first time, takes into account temporal information to identify meaningful sequences of actions in grasping and manipulation tasks . More specifically, we apply Deep Neural Networks to automatically learn features from hand posture images that consist of frames extracted from grasping and manipulation task videos with objects and external environmental constraints. For training purposes, videos are divided into intervals, each associated to a specific action by a human supervisor. The proposed algorithm combines a Convolutional Neural Network to detect the hand within each video frame and a Recurrent Neural Network to predict the hand action in the current frame, while taking into consideration the history of actions performed in the previous frames. Experimental validation has been performed on two datasets of dynamic hand-centric strategies, where subjects regularly interact with objects and environment. Proposed architecture achieved a very good classification accuracy on both datasets, reaching performance up to 94%, and outperforming state of the art techniques. The outcomes of this study can be successfully applied to robotics, e.g for planning and control of soft anthropomorphic manipulators. },
keywords = {convolutional neural network, deep learning, image understanding, machine vision, recurrent neural network, robotics},
pubstate = {published},
tppubtype = {article}
}
Humans are capable of complex manipulation interactions with the environment, relying on the intrinsic adaptability and compliance of their hands. Recently, soft robotic manipulation has attempted to reproduce such an extraordinary behavior, through the design of deformable yet robust end-effectors. To this goal, the investigation of human behavior has become crucial to correctly inform technological developments of robotic hands that can successfully exploit environmental constraint as humans actually do. Among the different tools robotics can leverage on to achieve this objective, deep learning has emerged as a promising approach for the study and then the implementation of neuro-scientific observations on the artificial side. However, current approaches tend to neglect the dynamic nature of hand pose recognition problems, limiting the effectiveness of these techniques in identifying sequences of manipulation primitives underpinning action generation, e.g. during purposeful interaction with the environment. In this work, we propose a vision-based supervised Hand Pose Recognition method which, for the first time, takes into account temporal information to identify meaningful sequences of actions in grasping and manipulation tasks . More specifically, we apply Deep Neural Networks to automatically learn features from hand posture images that consist of frames extracted from grasping and manipulation task videos with objects and external environmental constraints. For training purposes, videos are divided into intervals, each associated to a specific action by a human supervisor. The proposed algorithm combines a Convolutional Neural Network to detect the hand within each video frame and a Recurrent Neural Network to predict the hand action in the current frame, while taking into consideration the history of actions performed in the previous frames. Experimental validation has been performed on two datasets of dynamic hand-centric strategies, where subjects regularly interact with objects and environment. Proposed architecture achieved a very good classification accuracy on both datasets, reaching performance up to 94%, and outperforming state of the art techniques. The outcomes of this study can be successfully applied to robotics, e.g for planning and control of soft anthropomorphic manipulators. Davide, Bacciu; Antonio, Bruno
Text Summarization as Tree Transduction by Top-Down TreeLSTM Conference
Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI'18), IEEE, 2018.
Abstract | Links | BibTeX | Tags: deep learning, deep learning for graphs, neural networks, structured data processing, tree structured data, tree transductions
@conference{ssci2018,
title = {Text Summarization as Tree Transduction by Top-Down TreeLSTM},
author = {Bacciu Davide and Bruno Antonio},
url = {https://arxiv.org/abs/1809.09096},
doi = {10.1109/SSCI.2018.8628873},
year = {2018},
date = {2018-11-18},
booktitle = {Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI'18)},
pages = {1411-1418},
publisher = {IEEE},
abstract = {Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree transductions by extending the standard Long Short-Term Memory, considering the parent-child relationships in the structural recursion. The proposed model can achieve state of the art performance on sentence compression benchmarks, both in terms of accuracy and compression rate. },
keywords = {deep learning, deep learning for graphs, neural networks, structured data processing, tree structured data, tree transductions},
pubstate = {published},
tppubtype = {conference}
}
Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree transductions by extending the standard Long Short-Term Memory, considering the parent-child relationships in the structural recursion. The proposed model can achieve state of the art performance on sentence compression benchmarks, both in terms of accuracy and compression rate.