Category Archives: Students

New round of graduations

Quite intense weeks lately culminating in the graduation of several of my Ph.D. and M.Sc students. Quite interestingly this time they are all heading for positions in industry where I trust they will bring the appetite for science, technology and curiosity which I hope to have inspired in them.

Andrea Valenti completed his Ph.D. on learning representations for neural reasoners and he is now Machine Learning Engineer at Henesis

Alex Pasquali graduated in AI with honours and a thesis on hashtag#reinforcementlearning for virtual networks placement. He is now heading for an internship at Sauber: hope to spot him in the next F1 races!

Nicola Gugole graduated in AI with a thesis on identity preserving photo enhancement. Good luck for your adventure at Bending Spoons!

Sina Farhang Doust graduated in AI with a thesis bridging hashtag#nlp and hashtag#graph hashtag#neuralnetworks for legal text, and he is now bringing his skills to Aptus.AI.

Best of luck to all of you guys! Looking forward to collaborate again in the future.

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 JMLR paper

Couldn’t think of a better venue for my 99th research paper than the Journal of Machine Learning Research. Check out our work on deep and probabilistic learning for graphs. Terrific job by Federico Errica!

Davide Bacciu, Federico Errica, Alessio Micheli: Probabilistic Learning on Graphs via Contextual Architectures. In: Journal of Machine Learning Research, vol. 21, no. 134, pp. 1−39, 2020.

Graduation day

While classes are suspended, University is still open and today we had a great (epidemiologically-correct) graduation day with 5 of my students having discussed their B.Sc. and M.Sc. theses. Great works on graph neural networks applied to biochemistry and social-network data, tree transductions in image captioning, machine vision and genomic data processing. Congratulations to them all!

  • Alessio Gravina, Machine Learning prediction of compounds impact on Schizoprenia treatment, co-supervision by Corrado Priami and Kevin V. Grimes (Stanford University), M.Sc. in Computer Science & Artificial Intelligence
  • Davide Serramazza, Image captioning with structure generation, M.Sc. in Computer Science & Artificial Intelligence
  • Francesco Bachini, On the use of sequential learning models to estimate natural selection on Hiv from clinical samples, co-supervision by Matteo Fumagalli (Imperial College London), M.Sc. in Data Science and Business Informatics,
  • Gabriele Tenucci, A neural network-based intelligent filter for Youtube videos, B.Sc. in Computer Science
  • Lorenzo Gazzella, Analysing privacy-risks in social networks by deep learning for graphs, co-supervision with A. Monreale, B.Sc. in Computer Science
A snapshot of D. Serramazza Tree2Tree neural network for automated image captioning.

Artificial Intelligence in Medicine paper

Check out our newly accepted journal paper on discovering and measuring the confounding effect of data attributes in biomedical tasks. Preprint available on the Arvix. Congratulations to Elisa!

Elisa Ferrari, Alessandra Retico, Davide Bacciu: Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI). In: Artificial Intelligence in Medicine, vol. 103, 2020.