Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural Networks

TL;DR

This paper proposes a novel graph sparsification method for brain graphs that improves classification accuracy and interpretability by effectively removing noisy edges using task-relevant gradient information and shared edge selection.

Contribution

It introduces Interpretable Graph Sparsification (IGS), a new model that enhances GNN performance and interpretability by optimizing edge removal across multiple graphs with task relevance.

Findings

IGS improves classification accuracy by up to 5.1%.

IGS reduces edges by 55.0%, enhancing efficiency.

Shared edge selection outperforms separate selection.

Abstract

Brain graphs, which model the structural and functional relationships between brain regions, are crucial in neuroscientific and clinical applications involving graph classification. However, dense brain graphs pose computational challenges including high runtime and memory usage and limited interpretability. In this paper, we investigate effective designs in Graph Neural Networks (GNNs) to sparsify brain graphs by eliminating noisy edges. While prior works remove noisy edges based on explainability or task-irrelevant properties, their effectiveness in enhancing performance with sparsified graphs is not guaranteed. Moreover, existing approaches often overlook collective edge removal across multiple graphs. To address these issues, we introduce an iterative framework to analyze different sparsification models. Our findings are as follows: (i) methods prioritizing interpretability may not be suitable for graph sparsification as they can degrade GNNs' performance in graph classification tasks; (ii) simultaneously learning edge selection with GNN training is more beneficial than post-training; (iii) a shared edge selection across graphs outperforms separate selection for each graph; and (iv) task-relevant gradient information aids in edge selection. Based on these insights, we propose a new model, Interpretable Graph Sparsification (IGS), which enhances graph classification performance by up to 5.1% with 55.0% fewer edges. The retained edges identified by IGS provide neuroscientific interpretations and are supported by well-established literature.