@conference{Bacciu2021d,

title = {TEACHING - Trustworthy autonomous cyber-physical applications through human-centred intelligence},

editor = {Davide Bacciu and Siranush Akarmazyan and Eric Armengaud and Manlio Bacco and George Bravos and Calogero Calandra and Emanuele Carlini and Antonio Carta and Pietro Cassara and Massimo Coppola and Charalampos Davalas and Patrizio Dazzi and Maria Carmela Degennaro and Daniele Di Sarli and Jürgen Dobaj and Claudio Gallicchio and Sylvain Girbal and Alberto Gotta and Riccardo Groppo and Vincenzo Lomonaco and Georg Macher and Daniele Mazzei and Gabriele Mencagli and Dimitrios Michail and Alessio Micheli and Roberta Peroglio and Salvatore Petroni and Rosaria Potenza and Farank Pourdanesh and Christos Sardianos and Konstantinos Tserpes and Fulvio Tagliabò and Jakob Valtl and Iraklis Varlamis and Omar Veledar},

doi = {10.1109/COINS51742.2021.9524099},

year  = {2021},

date = {2021-08-23},

urldate = {2021-08-23},

booktitle = {Proceedings of the 2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS) },

abstract = {This paper discusses the perspective of the H2020 TEACHING project on the next generation of autonomous applications running in a distributed and highly heterogeneous environment comprising both virtual and physical resources spanning the edge-cloud continuum. TEACHING puts forward a human-centred vision leveraging the physiological, emotional, and cognitive state of the users as a driver for the adaptation and optimization of the autonomous applications. It does so by building a distributed, embedded and federated learning system complemented by methods and tools to enforce its dependability, security and privacy preservation. The paper discusses the main concepts of the TEACHING approach and singles out the main AI-related research challenges associated with it. Further, we provide a discussion of the design choices for the TEACHING system to tackle the aforementioned challenges},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Atzeni2021,

title = { Modeling Edge Features with Deep Bayesian Graph Networks},

author = {Daniele Atzeni and Davide Bacciu and Federico Errica and Alessio Micheli},

doi = {10.1109/IJCNN52387.2021.9533430},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},

publisher = {IEEE},

organization = {IEEE},

abstract = {We propose an extension of the Contextual Graph Markov Model, a deep and probabilistic machine learning model for graphs, to model the distribution of edge features. Our approach is architectural, as we introduce an additional Bayesian network mapping edge features into discrete states to be used by the original model. In doing so, we are also able to build richer graph representations even in the absence of edge features, which is confirmed by the performance improvements on standard graph classification benchmarks. Moreover, we successfully test our proposal in a graph regression scenario where edge features are of fundamental importance, and we show that the learned edge representation provides substantial performance improvements against the original model on three link prediction tasks. By keeping the computational complexity linear in the number of edges, the proposed model is amenable to large-scale graph processing.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Numeroso2021,

title = {MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks},

author = {Danilo Numeroso and Davide Bacciu},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{BacciuIJCNN2021,

title = {Federated Reservoir Computing Neural Networks},

author = {Davide Bacciu and Daniele Di Sarli and Pouria Faraji and Claudio Gallicchio and Alessio Micheli},

doi = {10.1109/IJCNN52387.2021.9534035},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},

publisher = {IEEE},

abstract = {A critical aspect in Federated Learning is the aggregation strategy for the combination of multiple models, trained on the edge, into a single model that incorporates all the knowledge in the federation. Common Federated Learning approaches for Recurrent Neural Networks (RNNs) do not provide guarantees on the predictive performance of the aggregated model. In this paper we show how the use of Echo State Networks (ESNs), which are efficient state-of-the-art RNN models for time-series processing, enables a form of federation that is optimal in the sense that it produces models mathematically equivalent to the corresponding centralized model. Furthermore, the proposed method is compliant with privacy constraints. The proposed method, which we denote as Incremental Federated Learning, is experimentally evaluated against an averaging strategy on two datasets for human state and activity recognition.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{BacciuPoddaIJCNN2021,

title = {GraphGen-Redux: a Fast and Lightweight Recurrent Model for Labeled Graph Generation},

author = {Davide Bacciu and Marco Podda},

doi = {10.1109/IJCNN52387.2021.9533743},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},

organization = {IEEE},

abstract = {The problem of labeled graph generation is gaining attention in the Deep Learning community. The task is challenging due to the sparse and discrete nature of graph spaces. Several approaches have been proposed in the literature, most of which require to transform the graphs into sequences that encode their structure and labels and to learn the distribution of such sequences through an auto-regressive generative model. Among this family of approaches, we focus on the Graphgen model. The preprocessing phase of Graphgen transforms graphs into unique edge sequences called Depth-First Search (DFS) codes, such that two isomorphic graphs are assigned the same DFS code. Each element of a DFS code is associated with a graph edge: specifically, it is a quintuple comprising one node identifier for each of the two endpoints, their node labels, and the edge label. Graphgen learns to generate such sequences auto-regressively and models the probability of each component of the quintuple independently. While effective, the independence assumption made by the model is too loose to capture the complex label dependencies of real-world graphs precisely. By introducing a novel graph preprocessing approach, we are able to process the labeling information of both nodes and edges jointly. The corresponding model, which we term Graphgen-redux, improves upon the generative performances of Graphgen in a wide range of datasets of chemical and social graphs. In addition, it uses approximately 78% fewer parameters than the vanilla variant and requires 50% fewer epochs of training on average.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{CastellanaCOLING2020,

title = {Learning from Non-Binary Constituency Trees via Tensor Decomposition},

author = {Daniele Castellana and Davide Bacciu},

year  = {2020},

date = {2020-12-08},

urldate = {2020-12-08},

booktitle = {PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS (COLING 2020)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {2020-07-19},

booktitle = {Proceedings  of the 2020 IEEE World Congress on Computational Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {2020-07-19},

booktitle = {Proceedings  of the 2020 IEEE World Congress on Computational Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@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},

urldate = {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 = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{icml2018,

title = {Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing},

author = {Bacciu Davide and Errica Federico and Micheli Alessio},

url = {https://arxiv.org/abs/1805.10636},

year  = {2018},

date = {2018-07-11},

urldate = {2018-07-11},

booktitle = {Proceedings of the 35th International Conference on Machine Learning (ICML 2018)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ijcnn2018,

title = {Concentric ESN: Assessing the Effect of Modularity in Cycle Reservoirs},

author = {Bacciu Davide and Bongiorno Andrea},

url = {https://arxiv.org/abs/1805.09244},

year  = {2018},

date = {2018-07-09},

urldate = {2018-07-09},

booktitle = {Proceedings  of the 2018 International Joint Conference on Neural Networks (IJCNN 2018) },

pages = {1-9},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{esann2018Tree,

title = {Mixture of Hidden Markov Models as Tree Encoder},

author = {Bacciu Davide and Castellana Daniele},

editor = {Michel Verleysen},

isbn = {978-287587047-6},

year  = {2018},

date = {2018-04-26},

urldate = {2018-04-26},

booktitle = {Proceedings  of the European Symposium on Artificial Neural Networks,  Computational Intelligence and Machine Learning (ESANN'18)},

pages = {543-548},

publisher = {i6doc.com},

address = {Louvain-la-Neuve, Belgium},

abstract = {The paper introduces a new probabilistic tree encoder based on a mixture of Bottom-up Hidden Tree Markov Models. The ability to recognise similar structures in data is experimentally assessed both in clusterization and classification tasks. The results of these preliminary experiments suggest that the model can be successfully used to compress the tree structural and label patterns in a vectorial representation.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{esann2018Tut,

title = {Bioinformatics and medicine in the era of deep learning},

author = {Bacciu Davide and Lisboa Paulo JG and Martin Jose D and Stoean Ruxandra and Vellido Alfredo},

editor = {Michel Verleysen},

url = {http://arxiv.org/abs/1802.09791},

isbn = {978-287587047-6},

year  = {2018},

date = {2018-04-26},

urldate = {2018-04-26},

booktitle = {Proceedings  of the European Symposium on Artificial Neural Networks,  Computational Intelligence and Machine Learning (ESANN'18)},

pages = {345-354},

publisher = {i6doc.com},

address = {Louvain-la-Neuve, Belgium},

abstract = {Many of the current scientific advances in the life sciences have their origin in the intensive use of data for knowledge discovery. In no area this is so clear as in bioinformatics, led by technological breakthroughs in data acquisition technologies. It has been argued that bioinformatics could quickly become the field of research generating the largest data repositories, beating other data-intensive areas such as high-energy physics or astroinformatics. Over the last decade, deep learning has become a disruptive advance in machine learning, giving new live to the long-standing connectionist paradigm in artificial intelligence. Deep learning methods are ideally suited to large-scale data and, therefore, they should be ideally suited to knowledge discovery in bioinformatics and biomedicine at large. In this brief paper, we review key aspects of the application of deep learning in bioinformatics and medicine, drawing from the themes covered by the contributions to an ESANN 2018 special session devoted to this topic.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{dl2017,

title = {Hidden Tree Markov Networks: Deep and Wide Learning for Structured Data},

author = {Bacciu Davide},

url = {https://arxiv.org/abs/1711.07784},

year  = {2017},

date = {2017-11-27},

urldate = {2017-11-27},

booktitle = {Proc. of the 2017 IEEE Symposium Series on Computational Intelligence (SSCI'17)},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{iml2017,

title = {On the Need of Machine Learning as a Service for the Internet of Things},

author = {Bacciu Davide and Chessa Stefano and Gallicchio Claudio and Micheli Alessio},

isbn = {978-1-4503-5243-7},

year  = {2017},

date = {2017-10-18},

booktitle = {To appear in the Proc. of the International Conference on Internet of Things and Machine Learning (IML 2017)},

journal = {Proc},

publisher = {ACM},

series = {International Conference Proceedings Series (ICPS)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ijcnn2017,

title = {DropIn: Making Neural Networks Robust to Missing Inputs by Dropout},

author = {Bacciu Davide and Crecchi Francesco and Morelli Davide},

url = {https://arxiv.org/abs/1705.02643},

doi = {10.1109/IJCNN.2017.7966106},

isbn = {978-1-5090-6182-2},

year  = {2017},

date = {2017-05-19},

urldate = {2017-05-19},

booktitle = {Proceedings  of the 2017 International Joint Conference on Neural Networks (IJCNN 2017) },

pages = {2080-2087},

publisher = {IEEE},

abstract = {The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of Dropout regularization, we propose a methodology, named DropIn, which efficiently trains a neural model as a committee machine of subnetworks, each capable of predicting with a subset of the original input features. We discuss the application of the DropIn methodology in the context of Reservoir Computing models and targeting applications characterized by input sources that are unreliable or prone to be disconnected, such as in pervasive wireless sensor networks and ambient intelligence. We provide an experimental assessment using real-world data from such application domains, showing how the Dropin methodology allows to maintain predictive performances comparable to those of a model without missing features, even when 20%–50% of the inputs are not available.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{esann2017,

title = {ELM Preference Learning for Physiological Data},

author = {Bacciu Davide and Colombo Michele and Morelli Davide and Plans David},

editor = {Michel Verleysen},

isbn = {978-2-875870384},

year  = {2017},

date = {2017-04-28},

urldate = {2017-04-28},

booktitle = {Proceedings  of the European Symposium on Artificial Neural Networks,  Computational Intelligence and Machine Learning (ESANN'17)},

pages = {99-104},

publisher = {i6doc.com},

address = {Louvain-la-Neuve, Belgium},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ie2016,

title = { Detecting socialization events in ageing people: the experienze of the DOREMI project},

author = {Bacciu Davide and Chessa Stefano and Ferro Erina and Fortunati Luigi and Gallicchio Claudio and La Rosa Davide and Llorente Miguel and Micheli Alessio and Palumbo Filippo and Parodi Oberdan and Valenti Andrea and Vozzi Federico},

doi = {10.1109/IE.2016.28},

issn = {2472-7571 },

year  = {2016},

date = {2016-10-27},

urldate = {2016-10-27},

booktitle = {Proceedings of the IEEE 12th International Conference on Intelligent Environments (IE 2016), },

pages = {132-135},

publisher = {IEEE},

address = {UK, London},

abstract = {The detection of socialization events is useful to build indicators about social isolation of people, which is an important indicator in e-health applications. On the other hand, it is rather difficult to achieve with non-invasive solutions. This paper reports about the currently work-in-progress on the technological solution for the detection of socialization events adopted in the DOREMI project.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{fun2016,

title = {An Investigation into Cybernetic Humor, or: Can Machines Laugh?},

author = {Bacciu Davide and Gervasi Vincenzo and Prencipe Giuseppe},

editor = {Erik D. Demaine and Fabrizio Grandoni},

url = {http://drops.dagstuhl.de/opus/volltexte/2016/5882},

doi = {10.4230/LIPIcs.FUN.2016.3},

issn = {1868-8969},

year  = {2016},

date = {2016-06-10},

booktitle = {Proceedings of  the 8th International Conference on Fun with Algorithms (FUN'16) },

volume = {49},

pages = {1-15},

publisher = {Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik},

series = {Leibniz International Proceedings in Informatics (LIPIcs)},

abstract = {The mechanisms of humour have been the subject of much study and investigation, starting with and up to our days. Much of this work is based on literary theories, put forward by some of the most eminent philosophers and thinkers of all times, or medical theories, investigating the impact of humor on brain activity or behaviour. Recent functional neuroimaging studies, for instance, have investigated the process of comprehending and appreciating humor by examining functional activity in distinctive regions of brains stimulated by joke corpora. Yet, there is precious little work on the computational side, possibly due to the less hilarious nature of computer scientists as compared to men of letters and sawbones. In this paper, we set to investigate whether literary theories of humour can stand the test of algorithmic laughter. Or, in other words, we ask ourselves the vexed question: Can machines laugh? We attempt to answer that question by testing whether an algorithm - namely, a neural network - can "understand" humour, and in particular whether it is possible to automatically identify abstractions that are predicted to be relevant by established literary theories about the mechanisms of humor. Notice that we do not focus here on distinguishing humorous from serious statements - a feat that is clearly way beyond the capabilities of the average human voter, not to mention the average machine - but rather on identifying the underlying mechanisms and triggers that are postulated to exist by literary theories, by verifying if similar mechanisms can be learned by machines. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}