SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks
Machine Learning
2025-10-15 v2 Machine Learning
Abstract
This paper introduces SpaPool, a novel pooling method that combines the strengths of both dense and sparse techniques for a graph neural network. SpaPool groups vertices into an adaptive number of clusters, leveraging the benefits of both dense and sparse approaches. It aims to maintain the structural integrity of the graph while reducing its size efficiently. Experimental results on several datasets demonstrate that SpaPool achieves competitive performance compared to existing pooling techniques and excels particularly on small-scale graphs. This makes SpaPool a promising method for applications requiring efficient and effective graph processing.
Keywords
Cite
@article{arxiv.2509.11675,
title = {SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks},
author = {Rodrigue Govan and Romane Scherrer and Philippe Fournier-Viger and Nazha Selmaoui-Folcher},
journal= {arXiv preprint arXiv:2509.11675},
year = {2025}
}