Article Classification with Graph Neural Networks and Multigraphs

TL;DR

This paper introduces a multi-graph approach to enhance article classification with GNNs by encoding multiple signals of relatedness, leading to improved performance on benchmark datasets.

Contribution

It presents a novel multi-graph representation that integrates various article relatedness signals, improving GNN classification performance over traditional single-graph methods.

Findings

Multi-graphs consistently outperform default graphs across models.

Multi-graphs enable shallow GNNs with simple architectures to match complex models.

Enhanced performance achieved with state-of-the-art textual embeddings.

Abstract

Classifying research output into context-specific label taxonomies is a challenging and relevant downstream task, given the volume of existing and newly published articles. We propose a method to enhance the performance of article classification by enriching simple Graph Neural Network (GNN) pipelines with multi-graph representations that simultaneously encode multiple signals of article relatedness, e.g. references, co-authorship, shared publication source, shared subject headings, as distinct edge types. Fully supervised transductive node classification experiments are conducted on the Open Graph Benchmark OGBN-arXiv dataset and the PubMed diabetes dataset, augmented with additional metadata from Microsoft Academic Graph and PubMed Central, respectively. The results demonstrate that multi-graphs consistently improve the performance of a variety of GNN models compared to the default graphs. When deployed with SOTA textual node embedding methods, the transformed multi-graphs enable simple and shallow 2-layer GNN pipelines to achieve results on par with more complex architectures.