Yearly Archives: 2019

ICLR2020 Paper

Our paper on benchmarking deep learning models for graph classification has been accepted at ICML 2020. Check it out!

Federico Errica, Marco Podda, Davide Bacciu, Alessio Micheli: A Fair Comparison of Graph Neural Networks for Graph Classification. Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020), 2020.

Neural networks on Treccani

Very proud of my little dissemination article on the Lingua Italiana magazine of Treccani. Check it out here (in Italian I am afraid)

Learning for graphs session @WCCI2020

I am happy to announce that I will be co-organizing a WCCI-2020 special session on Learning Representations for Structured Data together with Filippo Maria Bianchi (UIT), Thomas Gärtner (University of Nottingham), Nicolò Navarin (University of Padova) and Alessandro Sperduti (University of Padova)

Paper submission deadline is 15 January 2020 (extension pending).

Send you work through the conference submission site!

HTN code

Thanks to the invaluable work of my student Valerio De Caro, the code for the Hidden Tree Markov Network has been finally released. Check out Valerio’s github.

Big AI graduation day

Today we graduated a batch of 7 students from the first cycle of our AI M.Sc. of Computer science! Congratulations to my students of the AI curriculum, Andrea Cossu, Michele Cafagna, Federico Rossetto, Silvia Severini, as well as to Francesco Landolfi, from our previous M.Sc. Degree.

New H2020 Project

Now it looks official enough that I am going to coordinate the H2020 project TEACHING “A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence”. Project will start on January 2020. Stay tuned!

Researcher of the month

I am honoured that Università di Pisa has chosen me for the highlights of the Researcher of the Month for September 2019.

New accepted papers

A bunch of new papers on deep learning for graphs and neural language processing has just been accepted for publication. Check them out!

Davide Bacciu, Antonio Carta: Sequential Sentence Embeddings for Semantic Similarity. Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI'19), IEEE, 2019.

Michele Cafagna, Lorenzo De Mattei, Davide Bacciu, Malvina Nissim: Suitable doesn’t mean attractive. Human-based evaluation of automatically generated headlines. Proceedings of the 6th Italian Conference on Computational Linguistics (CLiC-it 2019), vol. 2481 , AI*IA series CEUR, 2019.

Davide Bacciu, Luigi Di Sotto: A non-negative factorization approach to node pooling in graph convolutional neural networks. Proceedings of the 18th International Conference of the Italian Association for Artificial Intelligence (AIIA 2019), Lecture Notes in Artificial Intelligence Springer-Verlag, 2019.

Internship @Stanford

Good luck to Alessio Gravina who is starting an intership at Stanford University for his M.Sc. project, co-supervised by me and Corrado Priami as part of the Spark program.

Special session on tensor methods for deep learning @ESANN2020

I am co-organizing with Danilo Mandic a special session on “Tensor Decompositions in Deep Learning” at ESANN 2020.

We welcome solid contributions and preliminary relevant results showing potential, limitations and challenges of new ideas related to the use of tensor decompositions in deep learning, neural networks, and machine learning at large.

Deadline for paper submission: 18 November 2019.

Prospective contributors/participants can contact me (or another co-organizer) for details.

Organized by Davide Bacciu (University of Pisa,Italy), Danilo Mandic (Imperial College, UK).

Davide Bacciu – Homepage

Full Professor – Dipartimento di Informatica, Università di Pisa