📚 Publications

BN-Pool: a Bayesian Nonparametric Approach to Graph Pooling

Daniele Castellana, Filippo Maria Bianchi

We introduce BN-Pool, the first clustering-based pooling method for GNNs that adaptively determines the number of supernodes in the pooled graph. This is done by partitioning the graph nodes into an unbounded number of clusters using a generative model based on a Bayesian non-parametric framework.

@misc{castellana2025bnpool,
  title={BN-Pool: a Bayesian Nonparametric Approach to Graph Pooling}, 
  author={Daniele Castellana and Filippo Maria Bianchi},
  year={2025},
  eprint={2501.09821},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2501.09821}, 
}

Interpreting Temporal Graph Neural Networks with Koopman Theory

Michele Guerra, Simone Scardapane, Filippo Maria Bianchi

We propose an XAI technique based on Koopman theory to interpret temporal graphs and the spatio-temporal Graph Neural Newtworks used to process them. The proposed approach allows to identify nodes and time steps when relevant events occur.

@misc{guerra2024interpretingtemporalgraphneural,
  title={Interpreting Temporal Graph Neural Networks with Koopman Theory}, 
  author={Michele Guerra and Simone Scardapane and Filippo Maria Bianchi},
  year={2024},
  eprint={2410.13469},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
}

MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks

Carlo Abate, Filippo Maria Bianchi

ICLR 2025

We propose a novel approach to compute the MAXCUT in attributed graphs, i.e., graphs with features associated with nodes and edges. Our approach is robust to the underlying graph topology and is fully differentiable, making it possible to find solutions that jointly optimize the MAXCUT along with other objectives. Based on the obtained MAXCUT partition, we implement a hierarchical graph pooling layer for Graph Neural Networks, which is sparse, differentiable, and particularly suitable for downstream tasks on heterophilic graphs.

@article{abate2024maxcutpool,
  title={MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks},
  author={Abate, Carlo and Bianchi, Filippo Maria},
  journal={arXiv preprint arXiv:2409.05100},
  year={2024}
}

Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling

Ivan Marisca, Cesare Alippi, Filippo Maria Bianchi

ICML 2024

Spatiotemporal graph neural networks achieve striking results by representing the relationships across time series as a graph. Nonetheless, most existing methods rely on the often unrealistic assumption that inputs are always available and fail to capture hidden spatiotemporal dynamics when part of the data is missing. In this work, we tackle this problem through hierarchical spatiotemporal downsampling. The input time series are progressively coarsened over time and space, obtaining a pool of representations that capture heterogeneous temporal and spatial dynamics. Conditioned on observations and missing data patterns, such representations are combined by an interpretable attention mechanism to generate the forecasts.

@inproceedings{marisca2024graph,
  title     = {Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling},
  author    = {Marisca, Ivan and Alippi, Cesare and Bianchi, Filippo Maria},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  pages     = {34846--34865},
  year      = {2024},
  volume    = {235},
  series    = {Proceedings of Machine Learning Research},
  publisher = {PMLR}
}