Publications

Journal and Conference papers

Journal papers

  • Lavado, D.; Micheletti, A., Bocchi, G.; Frosini, P.; Soares, C. SCENE-Net: Geometric induction for interpretable and low-resource 3D pole detection with Group-Equivariant Non-Expansive Operators. Computer Vision and Image Understanding, 2025, 262 (1), 104531. https://doi.org/10.1016/j.cviu.2025.104531.
  • Bocchi, G.; Frosini, P.; Micheletti, A.; Pedretti, A.; Palermo, G.; Gadioli, D.; Gratteri, C.; Lunghini, F.; Biswas, A. D.; Stouten, P. F. W.; Beccari, A. R.; Fava, A.; Talarico, C. GENEOnet: a breakthrough in protein binding pocket detection using group equivariant non-expansive operators. Scientific Reports, 2025, 15 (1), 34597. https://doi.org/10.1038/s41598-025-18132-5.
  • (Accepted version) Bocchi, G.; Frosini, P.; Micheletti, A.; Pedretti, A.; Gratteri, C.; Lunghini, F.; Beccari, A. R.; and, Talarico, C. GENEOnet: Statistical Analysis Supporting Explainability and Trustworthiness. Statistics, 2025, 59 (4), 1037–1062. https://doi.org/10.1080/02331888.2025.2478203.
  • Bocchi, G.; Ferri, M.; Frosini, P. A Novel Approach to Graph Distinction through GENEOs and Permutants. Scientific Reports, 2025, 15 (1), 6259. https://doi.org/10.1038/s41598-025-90152-7.
  • Bocchi, G.; Botteghi, S.; Brasini, M.; Frosini, P.; Quercioli, N. On the Finite Representation of Linear Group Equivariant Operators via Permutant Measures. Annals of Mathematics and Artificial Intelligence, 2023, 91, 465–487. https://doi.org/10.1007/s10472-022-09830-1.

Conference papers

  • Bocchi, G., Micheletti, A., Gratteri, C., Talarico, C. Prototypical Explanations in an AI Method for Protein Pocket Detection. In: Statistics for Innovation II. SIS 2025. Italian Statistical Society Series on Advances in Statistics. Springer, Cham. Genova, 2025, pp 195-200. https://doi.org/10.1007/978-3-031-96303-2_32
  • Bocchi, G.; Frosini, P.; Micheletti, A.; Pedretti, A.; Palermo, G.; Gadioli, D.; Gratteri, C.; Lunghini, F.; Beccari, A. R.; Fava, A.; Talarico, C. A Geometric XAI Approach to Protein Pocket Detection. In Joint Proceedings of the xAI 2024 Late-breaking Work, Demos and Doctoral Consortium co-located with the 2nd World Conference on eXplainable Artificial Intelligence (xAI-2024), Valletta, Malta, July 17-19, 2024; 2024; Vol. 3793, pp 217–224. Available at https://ceur-ws.org/Vol-3793/paper_28.pdf
  • Bocchi, G.; Micheletti, A.; Frosini, P.; Pedretti, A.; Beccari, A. R.; Lunghini, F.; Talarico, C.; Gratteri, C. Explainable Machine Learning based on Group Equivariant Non-Expansive Operators (GENEOs). Protein pocket detection: a case study. In Book of the Short Papers, Pearson: Ancona, 2023; pp 1191–1196. Available at https://it.pearson.com/content/dam/region-core/italy/pearson-italy/pdf/Docenti/Universit%C3%A0/bozza-book-compresso-new1.pdf
  • Bocchi, G.; Micheletti, A.; Frosini, P.; Pedretti, A.; Gratteri, C.; Lunghini, F.; Beccari, A. R.; Talarico, C. A new paradigm for Artificial Intelligence based on Group Equivariant Non-Expansive Operators (GENEOs) applied to protein pocket detection. In Proceedings of the Statistics and Data Science Conference; Pavia University Press: Pavia, 2023; pp 152–157. Available at https://www.paviauniversitypress.it/catalogo/proceedings-of-the-statistics-and-data-science-conference/6705

PhD thesis

  • Bocchi, G. Networks of Group Equivariant Non-Expansive Operators for Artificial Intelligence. Models, Applications and Interpretability. Supervisors: Micheletti A., Frosini P., Talarico C. PhD thesis, Department of Mathematics, University of Milan, Milan, Italy, 18 Feb 2025. https://hdl.handle.net/2434/1141329

Preprints

  • Bocchi, G.; Micheletti, A.; Nota, P.; Olper, A.; The impact of abnormal temperatures on crop yields in Italy: a functional quantile regression approach, Preprint at arXiv, 2026. Available at https://arxiv.org/abs/2601.12864.
  • Lavado, D.; Bocchi, G.; Frosini, P.; Micheletti, A.; Soares, C. Unlocking Geometric Induction: Advancing 3d Scene Understanding with Group Equivariant Non-Expansive Operators. Preprint at SSRN, 2024. Available at https://doi.org/10.2139/ssrn.4954143.