Publications

2026

1. PhD Thesis

   Towards Flexible and Expressive Generative Models for Tabular and Relational Data

   Davide Scassola and others

   2026

   Bib PDF

   @article{scassola2026towards,
     title = {Towards Flexible and Expressive Generative Models for Tabular and Relational Data},
     author = {Scassola, Davide and others},
     year = {2026},
     publisher = {University of Trieste},
   }

2. AAAI

   Graph-Conditional Flow Matching for Relational Data Generation

   Davide Scassola, Sebastiano Saccani, and Luca Bortolussi

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2026

   arXiv Bib Code

   @inproceedings{scassola2026graph,
     title = {Graph-Conditional Flow Matching for Relational Data Generation},
     author = {Scassola, Davide and Saccani, Sebastiano and Bortolussi, Luca},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {40},
     number = {30},
     pages = {25209--25217},
     year = {2026},
   }

3. UAI

   A Sobering Look at Tabular Data Generation via Probabilistic Circuits

   Davide Scassola, Dylan Ponsford, Adrián Javaloy, and 4 more authors

   In Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, 2026

   arXiv Bib Code

   @inproceedings{pmlr-v337-scassola26a,
     title = {A Sobering Look at Tabular Data Generation via Probabilistic Circuits},
     author = {Scassola, Davide and Ponsford, Dylan and Javaloy, Adri\'{a}n and Saccani, Sebastiano and Bortolussi, Luca and Gouk, Henry and Vergari, Antonio},
     booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence},
     pages = {6026--6063},
     year = {2026},
     editor = {Perković, Emilija and Malinsky, Daniel},
     volume = {337},
     series = {Proceedings of Machine Learning Research},
     publisher = {PMLR},
     url = {https://proceedings.mlr.press/v337/scassola26a.html},
   }

4. arXiv

   ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators

   Davide Scassola, Andrea Coser, and Sebastiano Saccani

   arXiv preprint arXiv:2605.14686, 2026

   arXiv Bib Code

   @article{scassola2026remia,
     title = {ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators},
     author = {Scassola, Davide and Coser, Andrea and Saccani, Sebastiano},
     journal = {arXiv preprint arXiv:2605.14686},
     year = {2026},
   }

2025

1. AAAI

   Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints

   Davide Scassola, Sebastiano Saccani, Ginevra Carbone, and 1 more author

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

   arXiv Bib Code

   @inproceedings{scassola2025zero,
     title = {Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints},
     author = {Scassola, Davide and Saccani, Sebastiano and Carbone, Ginevra and Bortolussi, Luca},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {39},
     number = {19},
     pages = {20302--20309},
     year = {2025},
   }

2024

1. NCA

   Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading

   Federico Cornalba, Constantin Disselkamp, Davide Scassola, and 1 more author

   Neural Computing and Applications, 2024

   arXiv Bib Code

   @article{cornalba2024multi,
     title = {Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading},
     author = {Cornalba, Federico and Disselkamp, Constantin and Scassola, Davide and Helf, Christopher},
     journal = {Neural Computing and Applications},
     volume = {36},
     number = {2},
     pages = {619--637},
     year = {2024},
     publisher = {Springer},
   }

2020

1. Master’s Thesis

   An Information-Theoretic Investigation Into Epigenetic Regulation of Gene Expression

   Davide Scassola, Matteo Marsili, and Guido Sanguinetti

   University of Trieste, SISSA, ICTP, 2020

   PDF