Graph Partition Neural Networks for Semi-Supervised Classification

TL;DR

This paper introduces Graph Partition Neural Networks (GPNN), a scalable approach for semi-supervised node classification on large graphs that combines local and global information propagation.

Contribution

GPNN extends GNNs with a novel graph partitioning method, enabling efficient processing of large-scale graphs while maintaining competitive accuracy.

Findings

GPNNs outperform or match state-of-the-art methods on various datasets.

GPNNs achieve similar performance as standard GNNs with fewer propagation steps.

A new fast graph partitioning variant improves scalability.

Abstract

We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating information between the subgraphs. To efficiently partition graphs, we experiment with several partitioning algorithms and also propose a novel variant for fast processing of large scale graphs. We extensively test our model on a variety of semi-supervised node classification tasks. Experimental results indicate that GPNNs are either superior or comparable to state-of-the-art methods on a wide variety of datasets for graph-based semi-supervised classification. We also show that GPNNs can achieve similar performance as standard GNNs with fewer propagation steps.