Saved in:
Bibliographic Details
Main Authors: Castellana, Daniele, Bianchi, Filippo Maria
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09821
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915904593330176
author Castellana, Daniele
Bianchi, Filippo Maria
author_facet Castellana, Daniele
Bianchi, Filippo Maria
contents We introduce BN-Pool, the first clustering-based pooling method for Graph Neural Networks that adaptively determines the number of supernodes in a coarsened graph. BN-Pool leverages a generative model based on a Bayesian nonparametric framework for partitioning graph nodes into an unbounded number of clusters. During training, the node-to-cluster assignments are learned by combining the supervised loss of the downstream task with an unsupervised auxiliary term, which encourages the reconstruction of the original graph topology while penalizing unnecessary proliferation of clusters. By automatically discovering the optimal coarsening level for each graph, BN-Pool preserves the performance of soft-clustering pooling methods while avoiding their typical redundancy by learning compact pooled graphs. The code is available at https://github.com/NGMLGroup/Bayesian-Nonparametric-Graph-Pooling.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09821
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BN-Pool: Bayesian Nonparametric Pooling for Graphs
Castellana, Daniele
Bianchi, Filippo Maria
Machine Learning
Probability
We introduce BN-Pool, the first clustering-based pooling method for Graph Neural Networks that adaptively determines the number of supernodes in a coarsened graph. BN-Pool leverages a generative model based on a Bayesian nonparametric framework for partitioning graph nodes into an unbounded number of clusters. During training, the node-to-cluster assignments are learned by combining the supervised loss of the downstream task with an unsupervised auxiliary term, which encourages the reconstruction of the original graph topology while penalizing unnecessary proliferation of clusters. By automatically discovering the optimal coarsening level for each graph, BN-Pool preserves the performance of soft-clustering pooling methods while avoiding their typical redundancy by learning compact pooled graphs. The code is available at https://github.com/NGMLGroup/Bayesian-Nonparametric-Graph-Pooling.
title BN-Pool: Bayesian Nonparametric Pooling for Graphs
topic Machine Learning
Probability
url https://arxiv.org/abs/2501.09821