Gabriele Ciravegna webpage

Gabriele Ciravegna

I am a Post Doc in the MAASAI (Models and Algorithms for Artificial Intelligence) research team of Inria.  I received the Ph.D. degree with honours from the University of Florence in 2022 under the supervision of Professor Marco Gori. In 2018, I received a master’s degree in Computer Engineering with honours at the Polytechnic of Turin. Besides machine learning, I also like football, volleyball, and playing the piano.

Contacts

You can write me at gabriele.ciravegna@inria.fr. Feel free also to contact me on Linkedin or Twitter!

Research

I have always been interested in the machine learning field. Nowadays, I am focused on overcoming the intrinsic limits of machine learning and neural networks. By combining neural networks with domain knowledge, I am studying how to tackle some of them, in particular in the contexts of Explainable AI, Adversarial Attacks and Active Learning.

I presented my works in several international venues such as IJCAI, AAAI, and IJCNN. I also serve as a reviewer in conferences and journals that are about Neural Networks, such as AAAI and IEEE TNNLS.

Take a look at the seminar I was invited to give at the University of Cambridge

Below is a list of my most recent publications. A complete and updated list of my publications is also available on ‪Google Scholar‬.
Publications
Conference papers:
  1. P Barbiero, G Ciravegna, F Giannini, P Lió, M Gori, S Melacci, “Entropy-based Logic Explanations of Neural Networks”, Proceedings of AAAI conference on Artificial Intelligence, 2022, (to appear)
  2. Gabriele Ciravegna, Francesco Giannini, Stefano Melacci, Marco Maggini, and Marco Gori. “A constraint-based approach to learning and explanation”. Proceedings of the AAAI Conference on Artificial Intelligence, pages 3658-3665, 2020, DOI: 10.1609/aaai.v34i04.5774.
  3. Gabriele Ciravegna, Francesco Giannini, Marco Gori, Marco Maggini, and Stefano Melacci. “Human-driven fol explanations of deep learning”. Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI), pages 2234-2240, 2020, DOI:  10.24963/ijcai.2020/309 
  4. Pietro Barbiero, Gabriele Ciravegna, Vincenzo Randazzo, and Giansalvo Cirrincione. “Topological gradient-based competitive learning”, 2021 International Joint Conference on Neural Networks (IJCNN), pages 1-8, 2021, DOI: 10.1109/IJCNN52387.2021.9533411.
Journal papers:
  1. Stefano Melacci, Gabriele Ciravegna, Angelo Sotgiu, Ambra Demontis, Battista Biggio, Marco Gori, and Fabio Roli. “Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers”, Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2021,  DOI: 10.1109/TPAMI.2021.3137564.
  2. Marta Lovino, Vincenzo Randazzo, Gabriele Ciravegna Pietro Barbiero, Elisa Ficarra and Giansalvo Cirrincione, “A survey on data integration for multi-omics sample clustering”, Neurocomputing journal, 2021, DOI: 10.1016/j.neucom.2021.11.094.
  3. Giansalvo Cirrincione, Gabriele Ciravegna, Pietro Barbiero, Vincenzo Randazzo, and Eros Pasero. “The GH-EXIN neural network for hierarchical clustering”. Neural Networks, pages: 57-73, 2020, DOI: 10.1016/j.neunet.2019.07.018

Comments are closed.