LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification

TL;DR

LightTopoGAT is a lightweight graph attention network that incorporates topological features like node degree and clustering coefficient, leading to improved graph classification accuracy with less computational overhead.

Contribution

The paper introduces a novel method that enhances graph attention networks with topological features, improving performance without increasing model complexity.

Findings

Achieves 6.6% accuracy improvement on MUTAG

Achieves 2.2% accuracy improvement on PROTEINS

Topological features significantly boost model performance

Abstract

Graph Neural Networks have demonstrated significant success in graph classification tasks, yet they often require substantial computational resources and struggle to capture global graph properties effectively. We introduce LightTopoGAT, a lightweight graph attention network that enhances node features through topological augmentation by incorporating node degree and local clustering coefficient to improve graph representation learning. The proposed approach maintains parameter efficiency through streamlined attention mechanisms while integrating structural information that is typically overlooked by local message passing schemes. Through comprehensive experiments on three benchmark datasets, MUTAG, ENZYMES, and PROTEINS, we show that LightTopoGAT achieves superior performance compared to established baselines including GCN, GraphSAGE, and standard GAT, with a 6.6 percent improvement in accuracy on MUTAG and a 2.2 percent improvement on PROTEINS. Ablation studies further confirm that these performance gains arise directly from the inclusion of topological features, demonstrating a simple yet effective strategy for enhancing graph neural network performance without increasing architectural complexity.