I am a Senior Researcher and Team lead at CENTAI Institute (CENTer for Artificial Intelligence, Turin, Italy). Previously, I was appointed as an Associate Professor (Maître de Conférences - tenured/permanent position) at the University of Lille (France), while I was a member of the Machine Learning in Information Networks team at INRIA Lille - Nord Europe.
Passionate about advancing machine learning, I am skilled in optimization, neural networks, clustering, and recommender systems. My research focuses on designing innovative decision-making algorithms and scalable methods to extract insights from large-scale networks, bridging theoretical rigor with real-world applications across academia and industry.
As AI/ML Team Lead at CENTAI, I steer a dynamic research team in pioneering machine learning innovations, with a focus on Fintech. We combine research and practical solutions in cutting-edge collaborations to build better intelligent systems.
In addition to my current professional activity in industrial research at CENTAI, I have also garnered industrial experience working at Bloomberg LP in Switzerland.
I received an MSc degree (Summa cum Laude) in Computer Science from the University of Insubria and a PhD in Machine Learning / Computer Science from the Milan University, working under the supervision of Prof. Nicolò Cesa-Bianchi and Prof. Claudio Gentile.
Recent professional activities
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - ECML PKDD 2023.
- Georgy Sokolov, Maximilian Thiessen, Margarita Akhmejanova, Fabio Vitale, Francesco Orabona.
Self-Directed Learning of Convex Labelings on Graphs.
Proceedings of the 36th International Conference on Algorithmic Learning Theory - ALT 2025. - Francesco Bonchi, Claudio Gentile, Francesco Paolo Nerini, André Panisson, Fabio Vitale.
Fast and Effective GNN Training through Sequences of Random Path Graphs.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining - KDD 2025. - Stephen Pasteris, Alberto Rumi, Maximilian Thiessen, Shota Saito, Atsushi Miyauchi, Fabio Vitale, Mark Herbster.
Bandits with abstention under expert advice.
Proceedings of the 38th conference on Neural Information Processing Systems - NeurIPS 2024. - Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale,
Nicolò Cesa-Bianchi.
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits.
Proceedings of the 27th International Conference on Artificial Intelligence and Statistics - AISTATS 2024 (oral presentation). - Stephen Pasteris, Alberto Rumi, Fabio Vitale, Nicolò Cesa-Bianchi.
Sum-max Submodular Bandits.
Proceedings of the 27th International Conference on Artificial Intelligence and Statistics - AISTATS 2024. - Stephen Pasteris, Fabio Vitale, Mark Herbster, Claudio Gentile, Andrè Panisson.
Adversarial Online Collaborative Filtering.
Proceedings of the 35th International Conference on Algorithmic Learning Theory - ALT 2024. - Stephen Pasteris, Mark Herbster, Fabio Vitale, Massimiliano Pontil.
A Gang of Adversarial Bandits.
Proceedings of the 35th conference on Neural Information Processing Systems - NeurIPS 2021. - Anand Rajagopalan, Fabio Vitale, Danny Vainstein, Gui Citovsky, Cecilia M. Procopiuc, Claudio Gentile.
Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation Guarantees.
Proc. of the 38th International Conference on Machine Learning - ICML 2021 - Stephen Pasteris, Ting He, Fabio Vitale, Shiqiang Wang, Mark Herbster.g
Online Learning of Facility Locations.
Proceedings of the 32nd International Conference on Algorithmic Learning Theory - ALT 2021. - Marco Bressan, Nicolò Cesa-Bianchi, Andrea Paudice, Fabio Vitale.
Correlation Clustering with Adaptive Similarity Queries.
Proceedings of the 33rd conference on Neural Information Processing Systems - NeurIPS 2019. - Fabio Vitale, Anand Rajagopalan, Claudio Gentile.
Flattening a Hierarchical Clustering through Active Learning.
Proceedings of the 33rd conference on Neural Information Processing Systems - NeurIPS 2019. - Stephen Pasteris, Fabio Vitale, Kevin Chan, Shiqiang Wang, Mark Herbster.
MaxHedge: Maximising a Maximum Online.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics - AISTATS 2019. - F. Vitale, N. Parotsidis, C. Gentile.
Online reciprocal recommendation with theoretical performance guarantees
Proceedings of the 32nd conference on Neural Information Processing Systems - NeurIPS 2018.
- S. Pasteris, F. Vitale, C. Gentile, M. Herbster.
On Similarity Prediction and Pairwise Clustering
Proceedings of the 29th International Conference on Algorithmic Learning Theory - ALT 2018. - G. Le Falher, N. Cesa-Bianchi, C. Gentile, F. Vitale.
On the troll-trust model for edge sign prediction in social networks
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics - AISTATS 2017. - N. Cesa-Bianchi, C. Gentile, F. Vitale, and G. Zappella.
Efficient Link Classification in Social Networks
International Conference on Computational Social Science - ICCSS 2015. - N. Cesa-Bianchi, C. Gentile, F. Vitale, G. Zappella
Random Spanning Trees and the Prediction of Weighted Graphs
Journal of Machine Learning Research, 14:1251-1284, 2013. - M.Herbster, S. Pasteris, F. Vitale.
Online Sum-Product Computation over Trees
Proceedings of the 26th Conference on Neural Information Processing Systems - NeurIPS 2012. - N. Cesa-Bianchi, C. Gentile, F. Vitale, and G. Zappella
A linear time active learning algorithm for link classification
Proceedings of the 26th Conference on Neural Information Processing Systems - NeurIPS 2012.
(Extended version of "A Linear Time Active Learning Algorithm for Link Classification", 29th International Conference on Machine Learning - ICML 2012 - Workshop: Mining and Learning with Graphs). - N. Cesa-Bianchi, C. Gentile, F. Vitale, and G. Zappella
A correlation clustering approach to link classification in signed networks
25th Annual Conference on Learning Theory. - COLT 2012 - JMLR Workshop and Conference Proceedings, 23:34.1-34.20, 2012. - N. Cesa-Bianchi, C. Gentile, F. Vitale
Predicting the labels of an unknown graph via adaptive exploration
Theoretical Computer Science, 412(19):1791-1804, 2011, Special Issue on Algorithmic Learning Theory 2009. - F. Vitale, N. Cesa-Bianchi, C. Gentile, and G. Zappella
See the tree through the lines: the Shazoo algorithm
Proceedings of the 25th Annual Conference on Neural Information Processing Systems - NeurIPS 2011.
- M. Herbster, S. Pasteris and F.Vitale
Efficient Prediction for Tree Markov Random Fields in a Streaming Model
25th Annual Conference on Neural Information Processing Systems - NeurIPS 2011 - Workshop: Discrete Optimization in Machine Learning (DISCML): Uncertainty, Generalization and Feedback. - N. Cesa-Bianchi, C. Gentile, F. Vitale, and G. Zappella
Active Learning on Graphs via Spanning Trees
24th Annual Conference on Neural Information Processing System - NeurIPS 2010 - Workshop: Networks Across Disciplines in Theory and Applications. - N. Cesa-Bianchi, C. Gentile, F. Vitale, and G. Zappella
Active Learning on Trees and Graphs
Proceedings of the 23rd Annual Conference on Learning Theory - COLT 2010. - N. Cesa-Bianchi, C. Gentile, F. Vitale, and G. Zappella
Random Spanning Trees and the Prediction of Weighted Graphs
Proceedings of the 27th International Conference on Machine Learning - ICML 2010. - N. Cesa-Bianchi, C. Gentile and F. Vitale
Fast and Optimal Algorithms for Weighted Graph Prediction
23rd Annual Conference on Neural Information Processing System - NeurIPS 2009 - Workshop: Analyzing Networks and Learning with Graphs. - N. Cesa-Bianchi, C. Gentile and F. Vitale
Learning Unknown Graphs
Proceedings of the 20th International Conference on Algorithmic Learning Theory - ALT 2009. - N. Cesa-Bianchi, C. Gentile and F. Vitale
Fast and Optimal Prediction on a Labeled Tree
Proceedings of the 22nd Annual Conference on Learning Theory - COLT 2009. - N. Cesa-Bianchi, C. Gentile and F. Vitale
Online Graph Prediction with Random Trees
22nd Annual Conference on Neural Information Processing System - NeurIPS 2008 - Workshop: New Challenges in Theoretical Machine Learning: Data Dependent Concept Spaces. - C. Gentile, F. Vitale and C. Brotto
On Higher-Order Perceptron Algorithms
Proceedings of the 21st Annual Conference on Neural Information Processing System - NeurIPS 2007.
Peer-reviewed publications
Industrial experience
- CENTAI (CENTer for Artificial Intelligence), Italy (2022 - present).
- Bloomberg LP, Switzerland (2012-2013).
Selected invited talks
-
Eurandom (Eindhoven, Netherland), 2024. Title: Fast and Effective GNN Training through Sequences of Random Path Graphs.
- NNAISENSE (Lugano, Switzerland), 2021. Title: Fast Clustering through Pairwise Similarity Information.
-
BrainTree (London, UK); ISI Foundation (Turin, Italy), 2020. Title: Compressing graph information for binary node classification.
- BrainTree (London, UK); INRIA Lille Nord Europe (Lille, France); Workshop FouLarD 2018
Miscellaneous
- Project funded by ANR
(Agence Nationale de la Recherche).
Project title: (PAMELA) - Personalized and decentrAlized MachinE Learning under constrAints (https://project.inria.fr/pamela/).
Duration: 2016-2020.
Partners (https://project.inria.fr/pamela/members/#asap): Inria Lille - Team Magnet, IRISA Rennes 1 University - Team ASAP, IRISA Rennes 1 University - Team Cidre, LIP6 - University of Paris 6 - Team MLIA.
Industrial partners: Snips, Mediego.
- Inria North-European Labs
(International partnership).
Project title: (RSS) - Rankings and Similarities in Signed graphs (https://raweb.inria.fr/rapportsactivite/RA2015/magnet/uid59.html).
Duration: late 2015 to late 2017.
Partners: Prof. Aristides Gionis (Data Mining Group, Aalto University, Finland) and Prof. Mark Herbster (Centre for Computational Statistics and Machine Learning, University College London, UK).
- SCAGLIA
(Scalable Graph Algorithms for Learning in Networked Data
JCJC "Jeunes Chercheuses et Jeunes Chercheurs" INS2I 2015
PI: Fabio Vitale).CRISTAL
Centre de Recherche en Informatique, Signal et Automatique de Lille. - MAGNET team
(Machine Learning in information NETworks). - PASCAL 2 Network of Excellence
(Pattern Analysis, Statistical Modelling and Computational Learning)
EU, Seventh Programme Framework. - Data-dependent geometries and structures
("pump-priming project" within Pascal2). - Google-sponsored project SPAN
(Scalable Prediction Algorithms for Networked Data - Google Research Award, January 2010). - PASCAL Network of Excellence
(Pattern Analysis, Statistical Modelling and Computational Learning)
EU, Sixth Programme Framework.
Visits to universities and research institutes
- May 2019: Google Research, New York (USA - Collaboration with Prof. Claudio Gentile).
- September 2018: University College London, Department of Computer Science (United Kingdom - Collaboration with Dr. Stephen Pasteris).
- April 2018: INRIA Lille Nord Europe (France - Member of the PhD committee of Géraud Le Falher).
- November 2017: University of Milan, Department of Computer Science (Italy - collaboration with Prof. Nicolò Cesa-Bianchi).
- March 2016; April 2016, May 2016: University of Milan, Department of Computer Science (Italy - collaboration with Prof. Nicolò Cesa-Bianchi and Prof. Claudio Gentile).
- July 2015; August 2015: Helsinki Aalto University, Department of Computer Science (Finland - collaboration with Prof. Aristides Gionis).
- May 2014: University of Milan, Department of Computer Science (Italy - collaboration with Prof. Nicolò Cesa-
Bianchi and Prof. Claudio Gentile).
- November 2013: University of Milan, Department of Computer Science (Italy - collaboration with Prof. Nicolò Cesa-Bianchi and Prof. Claudio Gentile);
University College London, Department of Computer Science (United Kingdom - collaboration with Prof. Mark Herbster);
University of Copenhagen, Department of Computer Science (Denmark - collaboration with Prof. Jyrki Katajainen)); - July 2013: Lille University & INRIA Lille - Nord Europe (France).
- August 2012: Microsoft Research, (Redmond, USA).
