Publications

Edited Books

[B2] Recent Trends in Learning From Data. Oneto, L. and Navarin, N. and Sperduti, N. and Anguita. D., Springer, 2020.

[B1] Recent Advances in Big Data and Deep Learning. Proceedings of the INNS Big Data and Deep Learning Conference INNSBDDL2019, held at Sestri Levante, Genova, Italy 16-18 April 2019. Editors: Luca Oneto, Nicolò Navarin, Alessandro Sperduti, Davide Anguita. [Springer]

Journals

[J11] Suppression of a SARS-CoV-2 outbreak in the Italian municipality of Vo'. Enrico Lavezzo, Elisa Franchin, Constanze Ciavarella, Gina Cuomo-Dannenburg, Luisa Barzon, Claudia Del Vecchio, Lucia Rossi, Riccardo Manganelli, Arianna Loregian, Nicolò Navarin, Davide Abate, Manuela Sciro, Stefano Merigliano, Ettore Decanale, Maria Cristina Vanuzzo, Valeria Besutti, Francesca Saluzzo, Francesco Onelia, Monia Pacenti, Saverio Parisi, Giovanni Carretta, Daniele Donato, Luciano Flor, Silvia Cocchio, Giulia Masi, Alessandro Sperduti, Lorenzo Cattarino, Renato Salvador, Michele Nicoletti, Federico Caldart, Gioele Castelli, Eleonora Nieddu, Beatrice Labella, Ludovico Fava, Matteo Drigo, Katy Gaythorpe, Imperial College London COVID-19 Response Team, Alessandra Brazzale, Stefano Toppo, Marta Trevisan, Vincenzo Baldo, Christl Donnelly, Neil Ferguson, Andrea Crisanti. In Nature, 2020. [link]

[J10] Multi-task learning for the prediction of wind power ramp events with deep neural networks, M.Dorado-Moreno, N.Navarin, P.A.Gutiérrez, L.Prieto, A.Sperduti, S.Salcedo-Sanz, C.Hervás-Martínez. Neural Networks, in press [link].

[J9] A framework for the Definition of Complex Structured Feature Spaces, Dinh V. Tran, Nicolò Navarin, Alessandro Sperduti. Neurocomputing, available online.

[J8] Scuba: scalable kernel-based gene prioritization, Guido Zampieri, Dinh Van Tran, Michele Donini, Nicolò Navarin, Fabio Aiolli, Alessandro Sperduti and Giorgio Valle. BMC Bioinformatics, BMC series 2018 19:23. [Open Access]

[J7] Learning with kernels: A Local Rademacher Complexity-based Analysis with Application to Graph Kernels, Luca Oneto, Nicolò Navarin, Michele Donini, Sandro Ridella, Alessandro Sperduti, Fabio Aiolli, Davide Anguita. IEEE Transactions on Neural Networks and Learning Systems, 2017. [IEEEXplore] doi: 10.1109/TNNLS.2017.2771830

[J6] Multilayer Graph Node Kernels: Stacking while Maintaining Convexity, Luca Oneto, Nicolò Navarin, Alessandro Sperduti, Davide Anguita. In Neural Processing Letters, 7 nov 2017. issn:"1573-773X" [Springer] doi:https://doi.org/10.1007/s11063-017-9742-z

[J5] A tree-based kernel for graphs with continuous attributes , Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In IEEE Transactions on Neural Networks and Learning Systems, 2017 [IEEEXplore] [arXiv] doi:10.1109/TNNLS.2017.2705694.

[J4] An efficient graph kernel method for non-coding RNA functional prediction, Nicolò Navarin and Fabrizio Costa. In Bioinformatics, Volume 33, Issue 17, 1 September 2017. doi: 10.1093/bioinformatics/btx295 [link].

[J3] Measuring the Expressivity of Graph Kernels through Statistical Learning Theory, Luca Oneto, Nicolò Navarin, Michele Donini, Alessandro Sperduti, Fabio Aiolli, Davide Anguita. In Neurocomputing, Volume 268, 13 December 2017, Pages 4-16 [pdf].

[J2] An Empirical Study on Budget-Aware Online Kernel Algorithms for Streams of Graphs, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In Neurocomputing,Volume 216, 5 December 2016, Pages 163–182. DOI: 10.1016/j.neucom.2016.07.029[arXiv] [FullText] [BibTeX].

[J1] Ordered Decompositional DAG Kernels Enhancements, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In Neurocomputing,Volume 192, 5 June 2016, Pages 92–103. DOI: 10.1016/j.neucom.2015.12.110 [arXiv] [Fulltext] [BibTeX]

Conferences

[C29] Explainable Predictive Process Monitoring. Riccardo Galanti, Bernat Coma-Puig, Massimiliano de Leoni, Josep Carmona, and Nicolò Navarin. In International Conference on Process Mining 2020, Padova, Italy.

[C28] Robotic Object Sorting via Deep Reinforcement Learning: a generalized approach. Luca Tagliapietra, Giorgio Nicola, Elisa Tosello, Nicolò Navarin, Stefano Ghidoni, Emanuele Menegatti. In IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) 2020, to appear.

[C27] Towards Online Discovery of Data-Aware Declarative Process Models from Event Streams. Nicolò Navarin, Matteo Cambiaso, Andrea Burattin, Fabrizio Maria Maggi, Luca Oneto and Alessandro Sperduti. In International Joint Conference on Neural Networks (IJCNN@WCCI)) 2020, to appear.

[C26] A Systematic Assessment of Deep Learning Models for Molecule Generation. Davide Rigoni, Nicolò Navarin and Alessandro Sperduti. In European Symposium on Artificial Neural Networks (ESANN) 2020, to appear.

[C25] Deep Recurrent Graph Neural Networks. Luca Pasa, Nicolò Navarin and Alessandro Sperduti.In European Symposium on Artificial Neural Networks (ESANN) 2020, to appear.

[C24] Linear Graph Convolutional Networks. Nicolò Navarin, Wolfgang Erb, Luca Pasa and Alessandro Sperduti. In European Symposium on Artificial Neural Networks (ESANN) 2020, to appear.

[C23] Learning Deep Fair Graph Neural Networks. Nicolò Navarin, Luca Oneto, Michele Donini.In European Symposium on Artificial Neural Networks (ESANN) 2020, to appear.

[C22] Learning Kernel-based Embeddings in Graph Neural Networks. Nicolò Navarin, Dinh Van Tran and Alessandro Sperduti.In European Conference on Artificial Intelligence (ECAI) 2020.

[W4] Training Graph Convolutional Neural Networks with Weisfeiler-Lehman Kernel. Dinh Van Tran, Nicolò Navarin and Alessandro Sperduti. In 2019 MLDM workshop, AI*IA conference, Cosenza, Italy, November 2019.

[C21] Smart Integration of Appliances for Food processing. Roberta D'Orazio, Davide Tommasin, Paride Babolin, Alessandro Bagante, Luciano Gamberini, Valeria Orso, Alessandro Sperduti, Nicolò Navarin. In ISPIM innovation Conference, Florence, Italy, June 16-19, 2019.

[C20] Universal Readout for Graph Convolutional Neural Networks. Nicolò Navarin, Dinh Van Tran and Alessandro Sperduti. In International Joint Conference on Neural Networks, Budapest, Hungary, July 14-19, 2019.[IEEExplore]

[C19] On the definition of complex structured feature spaces. Dinh V. Tran, Nicolò Navarin, Alessandro Sperduti. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, April 24-26, 2019, Bruges, Belgium. [pdf]

[C18] On filter size in graph convolutional networks, Dinh Van Tran, Nicolò Navarin and Alessandro Sperduti. In 2018 IEEE Symposium on Deep Learning (SSCI), November 18-21 2018, Bangalore, India [Preprint].

[C17] Extreme Graph Kernels for Online Learning on a Memory Budget, Nicolò Navarin, Giovanni Da San Martino, Alessandro Sperduti. In International Joint Conference on Neural Networks (IJCNN@WCCI), July 8-13, 2018, Rio de Janeiro, Brazil [IEEExplore].

[C16] Emerging Trends in Machine Learning: Beyond Conventional Methods and Data, Luca Oneto, Nicolò Navarin, Michele Donini and Davide Anguita. In 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, April 25-37, 2018, Bruges, Belgium [pdf].

[C15] DEEP: Decomposition Feature Enhancement Procedure for Graphs, Dinh Van Tran, Nicolò Navarin and Alessandro Sperduti. In 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, April 25-37, 2018, Bruges, Belgium (to appear) [pdf].

[C14] LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances, Nicolò Navarin, Beatrice Vincenzi, Mirko Polato and Alessandro Sperduti. In 2017 IEEE Symposium on Deep Learning @ SSCI. [IEEExplore] [arXiv].

[C13] Deep Graph Node Kernels: a Convex Approach, Luca Oneto, Nicolò Navarin, Alessandro Sperduti, and Davide Anguita. In 30th IEEE International Joint Conference on Neural Networks (IJCNN), 2017 [link].

[C12] Fast Hyperparameter Selection for Graph Kernels via Subsampling and Multiple Kernel Learning, Michele Donini, Nicolò Navarin, Ivano Lauriola, Fabio Aiolli and Fabrizio Costa. In 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 26-28 April 2017 [link].

[C11] Approximated Neighbors MinHash Graph Node Kernel, Nicolò Navarin and Alessandro Sperduti. In 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning [link] [poster].

[C10] Hyper-parameter tuning for graph kernels via Multiple Kernel Learning, Carlo M. Massimo, Nicolò Navarin and Alessandro Sperduti. In Neural Information Processing, Volume 9948 of the series Lecture Notes in Computer Science pp 214-223. DOI: 10.1007/978-3-319-46672-9_25 [Springer] [BibTeX] [Slides] [pdf]

[C9] Measuring the Expressivity of Graph Kernels through the Rademacher Complexity, Luca Oneto, Nicolò Navarin, Michele Donini, Alessandro Sperduti, Fabio Aiolli and Davide Anguita. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges (Belgium), 27-29 April 2016. ISBN 978-287587027-8 [pdf].

[C8] Advances in Learning with Kernels: Theory and Practice in a World of growing Constraints, Luca Oneto, Nicolò Navarin, Michele Donini, Fabio Aiolli and Davide Anguita. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges (Belgium), 27-29 April 2016. ISBN 978-287587027-8. [pdf].

[C7] Multiple Graph-Kernel Learning, Fabio Aiolli, Michele Donini, Nicolò Navarin and Alessandro Sperduti. In 2015 IEEE Symposium Series on Computational Intelligence , Cape Town (South Africa), pp. 1607-1614. doi: 10.1109/SSCI.2015.226.

[C6] Extending local features with contextual information in graph kernels, Nicolò Navarin, Alessandro Sperduti and Riccardo Tesselli. In Neural Information Processing, Lecture Notes in Computer Science, Volume 9492, 2015, pp 271-279. [bib][Springer] [arXiv]

[C5] Exploiting the ODD framework to define a novel effective graph kernel, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges (Belgium), 22 - 24 April 2015 - Proceedings, pp. 219-224. ISBN 978-287587014-8. [pdf] [bib]

[C4] Graph Kernels Exploiting Weisfeiler-Lehman Graph Isomorphism Test Extensions, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In Neural Information Processing, Lecture Notes in Computer Science, Volume 8835, 2014, pp 93-100. [link] preprint [arXiv]

[C3] A Lossy Counting Based Approach for Learning on Streams of Graphs on a Budget, Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti. In 23rd. International Joint Conference on Artificial Intelligence, August 3-9, 2013 - Beijing, China. [pdf] [bib]

[C2] A memory efficient graph kernel, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In WCCI 2012 IEEE World Congress on Computational Intelligence, IJCNN, June, 10-15, 2012 - Brisbane, Australia. [pdf]

[C1] A tree-based kernel for graphs, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In Proceedings of the Twelfth SIAM International Conference on Data Mining, Anaheim, California, April 26 - 28, 2012, p. 975-986. DOI: http://dx.doi.org/10.1137/1.9781611972825.84 [pdf] [Bib]

Workshops

[W4] Training Graph Convolutional Neural Networks with Weisfeiler-Lehman Kernel, Dinh Van Tran, Nicolò Navarin and Alessandro Sperduti. In MLDM workshop, International Conference of the Italian Association for Artificial Intelligence (AI*IA), 2019.

[W3] Pre-training Graph Neural Networks with Kernels, Nicolò Navarin, Dinh Van Tran and Alessandro Sperduti. In Machine Learning for Molecules and Materials NIPS 2018 Workshop.

[W2] On filter size in graph convolutional networks, Dinh Van Tran, Nicolò Navarin and Alessandro Sperduti. In MLDM workshop, International Conference of the Italian Association for Artificial Intelligence (AI*IA) 2018.

[W1] Model Approximation for Learning on Streams of Graphs on a Budget, Giovanni Da San Martino, Nicolò Navarin and Alessandro Sperduti. In workshop on Large-Scale Kernel Learning (LSKL@ICML), ICML 2015. [extended abstract]

PhD thesis

  • Learning with Kernels on Graphs: DAG-based kernels, data streams and RNA function prediction. Supervisor: Alessandro Sperduti. External committee: Karsten Borgwardt, Slobodan Vucetic [pdf]

Master's thesis

  • Graph kernels: a new DAG-based approach, Supervisor: Alessandro Sperduti, co-supervisor: Giovanni Sa San Martino.