@conference{Matteoni2022,

title = {Continual Learning for Human State Monitoring},

author = {Federico Matteoni and Andrea Cossu and Claudio Gallicchio and Vincenzo Lomonaco and Davide Bacciu},

editor = {Michel Verleysen},

url = {https://arxiv.org/pdf/2207.00010, Arxiv},

year  = {2022},

date = {2022-10-05},

urldate = {2022-10-05},

booktitle = {Proceedings of the 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2022)},

abstract = {Continual Learning (CL) on time series data represents a promising but under-studied avenue for real-world applications. We propose two new CL benchmarks for Human State Monitoring. We carefully designed the benchmarks to mirror real-world environments in which new subjects are continuously added. We conducted an empirical evaluation to assess the ability of popular CL strategies to mitigate forgetting in our benchmarks. Our results show that, possibly due to the domain-incremental properties of our benchmarks, forgetting can be easily tackled even with a simple finetuning and that existing strategies struggle in accumulating knowledge over a fixed, held-out, test subject.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Massidda2022,

title = {Knowledge-Driven Interpretation of Convolutional Neural Networks},

author = {Riccardo Massidda and Davide Bacciu},

year  = {2022},

date = {2022-09-20},

urldate = {2022-09-20},

booktitle = {Proceedings of the 2022 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2022)},

abstract = {Since the widespread adoption of deep learning solutions in critical environments, the interpretation of artificial neural networks has become a significant issue. To this end, numerous approaches currently try to align human-level concepts with the activation patterns of artificial neurons. Nonetheless, they often understate two related aspects: the distributed nature of neural representations and the semantic relations between concepts. We explicitly tackled this interrelatedness by defining a novel semantic alignment framework to align distributed activation patterns and structured knowledge. In particular, we detailed a solution to assign to both neurons and their linear combinations one or more concepts from the WordNet semantic network. Acknowledging semantic links also enabled the clustering of neurons into semantically rich and meaningful neural circuits. Our empirical analysis of popular convolutional networks for image classification found evidence of the emergence of such neural circuits. Finally, we discovered neurons in neural circuits to be pivotal for the network to perform effectively on semantically related tasks. We also contribute by releasing the code that implements our alignment framework.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Deep Features for CBIR with Scarce Data using Hebbian Learning},

author = {Gabriele Lagani and Davide Bacciu and Claudio Gallicchio and Fabrizio Falchi and Claudio Gennaro and Giuseppe Amato},

url = {https://arxiv.org/abs/2205.08935, Arxiv},

year  = {2022},

date = {2022-09-14},

urldate = {2022-09-14},

booktitle = {Proc. of the 19th International Conference on Content-based Multimedia Indexing (CBMI2022)},

abstract = { Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). In recent work, biologically inspired textit{Hebbian} learning algorithms have shown promises for DNN training. In this contribution, we study the performance of such algorithms in the development of feature extractors for CBIR tasks. Specifically, we consider a semi-supervised learning strategy in two steps: first, an unsupervised pre-training stage is performed using Hebbian learning on the image dataset; second, the network is fine-tuned using supervised Stochastic Gradient Descent (SGD) training. For the unsupervised pre-training stage, we explore the nonlinear Hebbian Principal Component Analysis (HPCA) learning rule. For the supervised fine-tuning stage, we assume sample efficiency scenarios, in which the amount of labeled samples is just a small fraction of the whole dataset. Our experimental analysis, conducted on the CIFAR10 and CIFAR100 datasets shows that, when few labeled samples are available, our Hebbian approach provides relevant improvements compared to various alternative methods. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sangermano2022,

title = {Sample Condensation in Online Continual Learning},

author = {Matteo Sangermano and Antonio Carta and Andrea Cossu and Vincenzo Lomonaco and Davide Bacciu

},

url = {https://arxiv.org/abs/2206.11849, Arxiv},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

booktitle = {Proceedings of the 2022 IEEE World Congress on Computational Intelligence},

publisher = {IEEE},

abstract = {Online Continual learning is a challenging learning scenario where the model observes a non-stationary stream of data and learns online. The main challenge is to incrementally learn while avoiding catastrophic forgetting, namely the problem of forgetting previously acquired knowledge while learning from new data. A popular solution in these scenario is to use a small memory to retain old data and rehearse them over time. Unfortunately, due to the limited memory size, the quality of the memory will deteriorate over time. In this paper we propose OLCGM, a novel replay-based continual learning strategy that uses knowledge condensation techniques to continuously compress the memory and achieve a better use of its limited size. The sample condensation step compresses old samples, instead of removing them like other replay strategies. As a result, the experiments show that, whenever the memory budget is limited compared to the complexity of the data, OLCGM improves the final accuracy compared to state-of-the-art replay strategies.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Valenti2022,

title = { Leveraging Relational Information for Learning Weakly Disentangled Representations },

author = {Andrea Valenti and Davide Bacciu

},

url = {https://arxiv.org/abs/2205.10056, Arxiv},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

booktitle = {Proceedings of the 2022 IEEE World Congress on Computational Intelligence},

publisher = {IEEE},

abstract = {Disentanglement is a difficult property to enforce in neural representations. This might be due, in part, to a formalization of the disentanglement problem that focuses too heavily on separating relevant factors of variation of the data in single isolated dimensions of the neural representation. We argue that such a definition might be too restrictive and not necessarily beneficial in terms of downstream tasks. In this work, we present an alternative view over learning (weakly) disentangled representations, which leverages concepts from relational learning. We identify the regions of the latent space that correspond to specific instances of generative factors, and we learn the relationships among these regions in order to perform controlled changes to the latent codes. We also introduce a compound generative model that implements such a weak disentanglement approach. Our experiments shows that the learned representations can separate the relevant factors of variation in the data, while preserving the information needed for effectively generating high quality data samples.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {The Infinite Contextual Graph Markov Model},

author = {Daniele Castellana and Federico Errica and Davide Bacciu and Alessio Micheli

},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

booktitle = {Proceedings of the 39th International Conference on Machine Learning (ICML 2022)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{carta2021ex,

title = {Ex-Model: Continual Learning from a Stream of Trained Models},

author = {Antonio Carta and Andrea Cossu and Vincenzo Lomonaco and Davide Bacciu},

url = {https://arxiv.org/pdf/2112.06511.pdf, Arxiv},

year  = {2022},

date = {2022-06-20},

urldate = {2022-06-20},

booktitle = {Proceedings of the CVPR 2022 Workshop on Continual Learning },

journal = {arXiv preprint arXiv:2112.06511},

pages = {3790-3799},

organization = {IEEE},

abstract = {Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt, and generalize continually in an efficient, effective, and scalable way is fundamental for a sustainable development of Artificial Intelligent systems. However, an agent-centric view of continual learning requires learning directly from raw data, which limits the interaction between independent agents, the efficiency, and the privacy of current approaches. Instead, we argue that continual learning systems should exploit the availability of compressed information in the form of trained models. In this paper, we introduce and formalize a new paradigm named "Ex-Model Continual Learning" (ExML), where an agent learns from a sequence of previously trained models instead of raw data. We further contribute with three ex-model continual learning algorithms and an empirical setting comprising three datasets (MNIST, CIFAR-10 and CORe50), and eight scenarios, where the proposed algorithms are extensively tested. Finally, we highlight the peculiarities of the ex-model paradigm and we point out interesting future research directions. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Serramazza2022,

title = {Learning image captioning as a structured transduction task},

author = {Davide Italo Serramazza and Davide Bacciu},

doi = {doi.org/10.1007/978-3-031-08223-8_20},

year  = {2022},

date = {2022-06-20},

urldate = {2022-06-20},

booktitle = {Proceedings of the 23rd International Conference on Engineering Applications of Neural Networks (EANN 2022)},

volume = {1600},

pages = {235–246},

publisher = {Springer},

series = {Communications in Computer and Information Science },

abstract = {Image captioning is a task typically approached by deep encoder-decoder architectures, where the encoder component works on a flat representation of the image while the decoder considers a sequential representation of natural language sentences. As such, these encoder-decoder architectures implement a simple and very specific form of structured transduction, that is a generalization of a predictive problem where the input data and output predictions might have substantially different structures and topologies. In this paper, we explore a generalization of such an approach by addressing the problem as a general structured transduction problem. In particular, we provide a framework that allows considering input and output information with a tree-structured representation. This allows taking into account the hierarchical nature underlying both images and sentences. To this end, we introduce an approach to generate tree-structured representations from images along with an autoencoder working with this kind of data. We empirically assess our approach on both synthetic and realistic tasks.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Lucchesi2022,

title = {Avalanche RL: a Continual Reinforcement Learning Library},

author = {Nicolò Lucchesi and Antonio Carta and Vincenzo Lomonaco and Davide Bacciu},

url = {https://arxiv.org/abs/2202.13657, Arxiv},

year  = {2022},

date = {2022-05-23},

urldate = {2022-05-23},

booktitle = {Proceedings of the 21st International Conference on Image Analysis and Processing (ICIAP 2021)},

abstract = {Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences). In this paper, we describe Avalanche RL, a library for Continual Reinforcement Learning which allows to easily train agents on a continuous stream of tasks. Avalanche RL is based on PyTorch and supports any OpenAI Gym environment. Its design is based on Avalanche, one of the more popular continual learning libraries, which allow us to reuse a large number of continual learning strategies and improve the interaction between reinforcement learning and continual learning researchers. Additionally, we propose Continual Habitat-Lab, a novel benchmark and a high-level library which enables the usage of the photorealistic simulator Habitat-Sim for CRL research. Overall, Avalanche RL attempts to unify under a common framework continual reinforcement learning applications, which we hope will foster the growth of the field. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{decaro2022aiasaservice,

title = {AI-as-a-Service Toolkit for Human-Centered Intelligence in Autonomous Driving},

author = {Valerio De Caro and Saira Bano and Achilles Machumilane and Alberto Gotta and Pietro Cassará and Antonio Carta and Christos Sardianos and Christos Chronis and Iraklis Varlamis and Konstantinos Tserpes and Vincenzo Lomonaco and Claudio Gallicchio and Davide Bacciu},

url = {https://arxiv.org/pdf/2202.01645.pdf, arxiv},

year  = {2022},

date = {2022-03-21},

urldate = {2022-03-21},

booktitle = {Proceedings of the 20th International Conference on Pervasive Computing and Communications (PerCom 2022)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Lanciano2021,

title = { Predictive Auto-scaling with OpenStack Monasca},

author = {Giacomo Lanciano and Filippo Galli and Tommaso Cucinotta and Davide Bacciu and Andrea Passarella},

url = {https://arxiv.org/abs/2111.02133, Arxiv},

doi = {10.1145/3468737.3494104},

year  = {2021},

date = {2021-12-06},

urldate = {2021-12-06},

booktitle = {Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2021)},

pages = {1-10},

abstract = {Cloud auto-scaling mechanisms are typically based on reactive automation rules that scale a cluster whenever some metric, e.g., the average CPU usage among instances, exceeds a predefined threshold. Tuning these rules becomes particularly cumbersome when scaling-up a cluster involves non-negligible times to bootstrap new instances, as it happens frequently in production cloud services.

To deal with this problem, we propose an architecture for auto-scaling cloud services based on the status in which the system is expected to evolve in the near future. Our approach leverages on time-series forecasting techniques, like those based on machine learning and artificial neural networks, to predict the future dynamics of key metrics, e.g., resource consumption metrics, and apply a threshold-based scaling policy on them. The result is a predictive automation policy that is able, for instance, to automatically anticipate peaks in the load of a cloud application and trigger ahead of time appropriate scaling actions to accommodate the expected increase in traffic.

We prototyped our approach as an open-source OpenStack component, which relies on, and extends, the monitoring capabilities offered by Monasca, resulting in the addition of predictive metrics that can be leveraged by orchestration components like Heat or Senlin. We show experimental results using a recurrent neural network and a multi-layer perceptron as predictor, which are compared with a simple linear regression and a traditional non-predictive auto-scaling policy. However, the proposed framework allows for the easy customization of the prediction policy as needed. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{BacciuCAIP2021,

title = {Towards Functional Safety Compliance of Recurrent Neural Networks},

author = {Davide Bacciu and Antonio Carta and Daniele Di Sarli and Claudio Gallicchio and Vincenzo Lomonaco and Salvatore Petroni},

url = {https://aiforpeople.org/conference/assets/papers/CAIP21-P09.pdf, Open Access PDF},

year  = {2021},

date = {2021-11-20},

booktitle = {Proceedings of the International Conference on AI for People (CAIP 2021)},

abstract = {Deploying Autonomous Driving systems requires facing some novel challenges for the Automotive industry. One of the most critical aspects that can severely compromise their deployment is Functional Safety. The ISO 26262 standard provides guidelines to ensure Functional Safety of road vehicles. However, this standard is not suitable to develop Artificial Intelligence

based systems such as systems based on Recurrent Neural Networks (RNNs). To address this issue, in this paper we propose a new methodology, composed of three steps. The first step is the robustness evaluation of the RNN against inputs perturbations. Then, a proper set of safety measures must be defined according to the model’s robustness, where less robust models will require stronger mitigation. Finally, the functionality of the entire system must be extensively tested

according to Safety Of The Intended Functionality (SOTIF) guidelines, providing quantitative results about the occurrence of unsafe scenarios, and by evaluating appropriate Safety Performance Indicators.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Cossu2021,

title = { Continual Learning with Echo State Networks },

author = {Andrea Cossu and Davide Bacciu and Antonio Carta and Claudio Gallicchio and Vincenzo Lomonaco},

editor = {Michel Verleysen},

url = {https://arxiv.org/abs/2105.07674, Arxiv},

doi = {10.14428/esann/2021.ES2021-80},

year  = {2021},

date = {2021-10-06},

urldate = {2021-10-06},

booktitle = {Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning  (ESANN 2021)

},

volume = {275-280},

abstract = { Continual Learning (CL) refers to a learning setup where data is non stationary and the model has to learn without forgetting existing knowledge. The study of CL for sequential patterns revolves around trained recurrent networks. In this work, instead, we introduce CL in the context of Echo State Networks (ESNs), where the recurrent component is kept fixed. We provide the first evaluation of catastrophic forgetting in ESNs and we highlight the benefits in using CL strategies which are not applicable to trained recurrent models. Our results confirm the ESN as a promising model for CL and open to its use in streaming scenarios. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Bacciu2021c,

title = { Deep learning for graphs},

author = {Davide Bacciu and Filippo Maria Bianchi and Benjamin Paassen and Cesare Alippi},

editor = {Michel Verleysen},

doi = {10.14428/esann/2021.ES2021-5},

year  = {2021},

date = {2021-10-06},

urldate = {2021-10-06},

booktitle = {Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning  (ESANN 2021)},

pages = {89-98},

abstract = { Deep learning for graphs encompasses all those models endowed with multiple layers of abstraction, which operate on data represented as graphs. The most common building blocks of these models are graph encoding layers, which compute a vector embedding for each node in a graph based on a sum of messages received from its neighbors. However, the family also includes architectures with decoders from vectors to graphs and models that process time-varying graphs and hypergraphs. In this paper, we provide an overview of the key concepts in the field, point towards open questions, and frame the contributions of the ESANN 2021 special session into the broader context of deep learning for graphs. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Dukic2021,

title = {Inductive learning for product assortment graph completion},

author = {Haris Dukic and Georgios Deligiorgis and Pierpaolo Sepe and Davide Bacciu and Marco Trincavelli},

editor = {Michel Verleysen},

doi = {10.14428/esann/2021.ES2021-73},

year  = {2021},

date = {2021-10-06},

urldate = {2021-10-06},

booktitle = {Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning  (ESANN 2021)},

pages = {129-134},

abstract = { Global retailers have assortments that contain hundreds of thousands of products that can be linked by several types of relationships like style compatibility, "bought together", "watched together", etc. Graphs are a natural representation for assortments, where products are nodes and relations are edges. Relations like style compatibility are often produced by a manual process and therefore do not cover uniformly the whole graph. We propose to use inductive learning to enhance a graph encoding style compatibility of a fashion assortment, leveraging rich node information comprising textual descriptions and visual data. Then, we show how the proposed graph enhancement improves substantially the performance on transductive tasks with a minor impact on graph sparsity. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Valenti2021b,

title = {Calliope - A Polyphonic Music Transformer},

author = {Andrea Valenti and Stefano Berti and Davide Bacciu},

editor = {Michel Verleysen},

url = { The polyphonic nature of music makes the application of deep learning to music modelling a challenging task. On the other hand, the Transformer architecture seems to be a good fit for this kind of data. In this work, we present Calliope, a novel autoencoder model based on Transformers for the efficient modelling of multi-track sequences of polyphonic music. The experiments show that our model is able to improve the state of the art on musical sequence reconstruction and generation, with remarkably good results especially on long sequences. },

doi = {10.14428/esann/2021.ES2021-63},

year  = {2021},

date = {2021-10-06},

urldate = {2021-10-06},

booktitle = {Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning  (ESANN 2021)},

pages = {405-410},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@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}

}