Publications
2026
A Non-Aggregative Quantification Method for Graph Nodes
In ECML/PKDD Workshop on Quantification and Classification under Dataset Shift (QCDS 2026).
Network Quantification on Neuromorphic Hardware: Proof-of-concept with Randomized Ising Models
In ECML/PKDD Workshop on Quantification and Classification under Dataset Shift (QCDS 2026).
A method for the systematic generation of graph XAI benchmarks via Weisfeiler–Leman coloring
Data Mining and Knowledge Discovery, 40(4), pp. 42.
Machine learning prediction of mechanical dilatation in transvenous lead extraction for cardiac device-related infections: insights from a high-volume centre
Journal of Interventional Cardiac Electrophysiology.
2025
An Empirical Investigation of Shortcuts in Graph Learning
In Graph-Based Representations in Pattern Recognition, pp. 147–156. Springer Nature Switzerland.
Graph Diffusion that can Insert and Delete
In Advances in Neural Information Processing Systems, pp. 78375–78401. Curran Associates, Inc..
Towards Efficient Molecular Property Optimization with Graph Energy Based Models
In Proceedings of the 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 289–294.
Analyzing Explanations of Deep Graph Networks through Node Centrality and Connectivity
In Discovery Science, pp. 295–309. Springer Nature Switzerland.
Relating Explanations with the Inductive Biases of Deep Graph Networks
In AIxIA 2024 - Advances in Artificial Intelligence, pp. 175–187. Springer Nature Switzerland.
Investigating Time-Scales in Deep Echo State Networks for Natural Language Processing
In Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions, pp. 188–200. Springer Nature Switzerland.
A descriptor-free machine learning framework to improve antigen discovery for bacterial pathogens
PLOS ONE, 20(6), pp. 1–22.
Misinformation mitigation in online social networks using continual learning with graph neural networks
Online Social Networks and Media, 50, pp. 100340.
Bridging XAI and spectral analysis to investigate the inductive biases of deep graph networks
Machine Learning, 114, pp. 257.
Sensitivity analysis on Protein-Protein Interaction Networks through Deep Graph Networks
BMC Bioinformatics, 26, pp. 124.
2024
Predictive machine learning model for mechanical dilatation in transvenous lead extraction procedures
European Heart Journal Supplements, 26(Supplement 2), pp. ii82–ii82.
How Much Do DNA and Protein Deep Embeddings Preserve Biological Information?
In Computational Methods in Systems Biology, pp. 209–225. Springer Nature Switzerland.
Classifier-free graph diffusion for molecular property targeting
In 4th Workshop on Graphs and More Complex Structures for Learning and Reasoning, co-located with AAAI 2024.
Classifier-Free Graph Diffusion for Molecular Property Targeting
In Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD, pp. 318–335. Springer Nature Switzerland.
XAI and Bias of Deep Graph Networks
In Proceedings of the 32nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 41–46.
Explaining Graph Classifiers by Unsupervised Node Relevance Attribution
In Explainable Artificial Intelligence, pp. 63–74. Springer Nature Switzerland.
Classification of Neisseria meningitidis genomes with a bag-of-words approach and machine learning
iScience, 27(3).
2023
Graph Representation Learning
In Proceedings of the 31st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 1–10.
Exploiting the structure of biochemical pathways to investigate dynamical properties with neural networks for graphs
Bioinformatics, 39(11).
Deep Graph Networks for Drug Repurposing with Multi-Protein Targets
IEEE Transactions on Emerging Topics in Computing, pp. 1–14.
2022
Deep Learning in Cheminformatics
In Deep Learning in Biology and Medicine, pp. 157–195. World Scientific Publishing.
2021
A rigorous evaluation of embeddings-based vs. feature-based machine learning models for protein antigenicity prediction
In 10th Italian Workshop on Machine Learning and Data Mining, part of AIxIA 2021.
Classification of Biochemical Pathway Robustness with Neural Networks for Graphs
In Communications in Computer and Information Science, pp. 215–239. Springer International Publishing.
GraphGen-Redux: A Fast and Lightweight Recurrent Model for Labeled Graph Generation
In International Joint Conference on Neural Networks, pp. 1–8. IEEE.
2020
Biochemical Pathway Robustness Prediction with Graph Neural Networks
In Proceedings of the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 121–126.
A Deep Generative Model for Fragment-Based Molecule Generation
In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics.
A Fair Comparison of Graph Neural Networks for Graph Classification
In 8th International Conference on Learning Representations.
Prediction of Dynamical Properties of Biochemical Pathways with Graph Neural Networks
In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS, pp. 32–43. SCITEPRESS.
Edge-based sequential graph generation with recurrent neural networks
Neurocomputing, 416, pp. 177–189.
2019
Preliminary Results on Predicting Robustness of Biochemical Pathways through Machine Learning on Graphs
In Pre-proceedings of the 8th International Symposium From Data to Models and Back (DataMod).
Graph generation by sequential edge prediction
In Proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 95–100.