Revisiting Edge Pooling in Graph Neural Networks
Francesco Landolfi · 2022
Sparse pooling methods for graph neural networks typically perform graph reduction by keeping only the top-k vertices according to an adaptive scoring function.Although fast and scalable, these methods destroy the relational information of the graph and possibly make it disconnected.EdgePool is one of the few sparse alternatives that preserve the connectivity of the input graph by performing a series of edge contractions according to an adaptive scoring of the edges, but it has the drawback of being sequential and not scalable on large scale graphs.In this paper we show that EdgePool can be efficiently computed adapting a well-known parallel algorithm from literature, and we also propose a novel, parallel alternative that leverages on an adaptive scoring function of the nodes.We test both methods on standard benchmark datasets, showing that they generally outperform other sparse pooling methods from the literature. * I would like to thank Davide Bacciu and Alessio Conte