Author Archives: DAVIDE BACCIU

New year updates

Quite a busy semester, hence long time no posts. Lets start the year with a bunch of good news.

Our book on Deep Learning in Biology and Medicine, edited with Paulo Lisboa, and Alfredo Vellido, is finally available for preorder. Check it out here!

Davide Bacciu, Paulo J. G. Lisboa, Alfredo Vellido: Deep Learning in Biology and Medicine. World Scientific Publisher, 2022, ISBN: 978-1-80061-093-4.

July 2022 is going to be a busy month in Padova with the organization of IEEE WCCI 2022, including

  • 1st Pervasive Artificial Intelligence Workshop co-chaired with Antonio Carta (Università di Pisa), Patrizio Dazzi (ISTI-CNR),  Magdalini Eirinaki (San Jose State University), Iraklis Varlamis (Harokopio University of Athens) – Deadline early April 2022
  • Deep learning for graphs special session, co-chaired with Shirui Pan (Monash University), Daniele Grattarola (IDSIA), Miao Zhang (Aalborg University), Nicolò Navarin (University of Padova), Feng Xia (Federation University Australia), Daniele Zambon (IDSIA) – Deadline 31st January 2022

ICML 2021 paper

Extremely happy and excited to share that our paper “Graph Mixture Density Networks” has been accepted for publication at ICML 2021! Huge congrats to Federico Errica for his second ICML paper and to Alessio Micheli who shares with me Federico’s supervision towards a brilliant Ph.D!

Check out the paper (soon on Arxiv in camera-ready form) to discover how we introduced first model for learning multi-modal output distributions conditioned on arbitrary graphs, and its application to epidemiology.

Federico Errica, Davide Bacciu, Alessio Micheli: Graph Mixture Density Networks. Proceedings of the 38th International Conference on Machine Learning (ICML 2021), PMLR, 2021.

IJCNN 2021 papers

Our group had 4 papers recently accepted to the upcoming International Joint Conference on Neural Networks! Much work on deep learning for graphs, including a novel edge-based model, an efficient graph generation approach and an explanation method for the chemical domain. Also a first proposal for an efficient federation of reservoir computing methods, part of our H2020 TEACHING efforts. Preprints soon on the Arxiv!

Daniele Atzeni, Davide Bacciu, Federico Errica, Alessio Micheli: Modeling Edge Features with Deep Bayesian Graph Networks. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), IEEE IEEE, 2021.

Danilo Numeroso, Davide Bacciu: MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), IEEE 2021.

Davide Bacciu, Daniele Di Sarli, Pouria Faraji, Claudio Gallicchio, Alessio Micheli: Federated Reservoir Computing Neural Networks. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), IEEE, 2021.

Davide Bacciu, Marco Podda: GraphGen-Redux: a Fast and Lightweight Recurrent Model for Labeled Graph Generation. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), IEEE 2021.

New AI Graduates!

Another big graduation day today, with plenty of contributions from our group! Congratulations to all students for their achievement. Check them out below. Pleanty of cool stuff including distillation-based continual learning, medical image analysis and generation, reinforcement learning and quantum computing as well as emotion understanding. Well done to all of you!

Apprendimento con rinforzo: un’esperienza d’uso nel gioco Asso Pigliatutto, Enrico Tomasi, Laurea in Informatica, Università di Pisa, A.A. 2019/2020

Distilled Replay: Mitigating Forgetting through Dataset Distillation (co-supervised with A. Carta, A. Cossu), Andrea Rosasco, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

ANSIA: A Neural System that Infers Affects (co-supervised with C.Gallicchio), Matteo Montalbetti, Laurea in Informatica, Università di Pisa, A.A. 2019/2020

Quantum Control via Deep Reinforcement Learning using IBMQ platform and Qiskit Pulse (co-supervision by Enrico Prati, CNR), Rudy Semola, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

Tomography reconstruction with end-to-end neural networks, Matteo Ronchetti, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

Dynamic neural networks for COVID-19 severity prediction from lung ultrasound (co-supervised with F. Faita, IFC-CNR), Ruggiero Santo, Laurea Magistrale in Informatica (Curriculum AI), Università di Pisa, A.A. 2019/2020

Neurips 2020 WS papers

Excellent result by our group in the upcoming NeurIPS 2020 workshops with four accepted papers.
Congrats to Antonio Carta, Francesco Landolfi, Danilo Numeroso and Matteo Ronchetti!

Preprints coming up..

Matteo Ronchetti, Davide Bacciu: Generative Tomography Reconstruction. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Deep Learning and Inverse Problems, 2020.

Davide Bacciu, Alessio Conte, Roberto Grossi, Francesco Landolfi, Andrea Marino: K-plex Cover Pooling for Graph Neural Networks. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Learning Meets Combinatorial Algorithms, 2020.

Davide Bacciu, Danilo Numeroso: Explaining Deep Graph Networks with Molecular Counterfactuals. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Machine Learning for Molecules - Accepted as Contributed Talk (Oral), 2020.

Antonio Carta, Alessandro Sperduti, Davide Bacciu : Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization . 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Workshop on Beyond BackPropagation: Novel Ideas for Training Neural Architectures, 2020.

New M.Sc. Graduates in AI

Big graduation day in the ML family with 3 newly graduated students (two cum laude!) on topics ranging from neuro-probabilistic models for graphs, interpretability of graph neural networks for chemistry and cognitive architectures for creativity. Congratulations!

Daniele Arioli, CognAC: a cognitive architecture based on Information Dynamics of Thinking, co-supervised with V. Gervasi, M.Sc. in Computer Science & Artificial Intelligence

Valerio De Caro, Graph Relative Density Networks, M.Sc. in Computer Science & Artificial Intelligence

Danilo Numeroso, Explaining Deep Graph Networks By Structured Counterfactual Explanations, M.Sc. in Computer Science & Artificial Intelligence

Paper Accepted at COLING 2020

Congratulations to Daniele Castellana for having his paper accepted at COLING 2020. Check it out if you are interested in higher-order neural networks for parse trees using tensor decompositions (soon on the Arxiv!).

Daniele Castellana, Davide Bacciu: Learning from Non-Binary Constituency Trees via Tensor Decomposition. PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS (COLING 2020), 2020.