TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
This work addresses the lack of interpretability in GNNs for critical decision-making, offering a novel method to handle complex and varied rationale subgraphs, though it is incremental in advancing interpretable graph learning.
The paper tackles the problem of interpretability in Graph Neural Networks (GNNs) by proposing TopInG, a topological framework that uses persistent homology to identify rationale subgraphs, resulting in improved predictive accuracy and interpretation quality over state-of-the-art methods.
Graph Neural Networks (GNNs) have shown remarkable success across various scientific fields, yet their adoption in critical decision-making is often hindered by a lack of interpretability. Recently, intrinsically interpretable GNNs have been studied to provide insights into model predictions by identifying rationale substructures in graphs. However, existing methods face challenges when the underlying rationale subgraphs are complex and varied. In this work, we propose TopInG: Topologically Interpretable Graph Learning, a novel topological framework that leverages persistent homology to identify persistent rationale subgraphs. TopInG employs a rationale filtration learning approach to model an autoregressive generation process of rationale subgraphs, and introduces a self-adjusted topological constraint, termed topological discrepancy, to enforce a persistent topological distinction between rationale subgraphs and irrelevant counterparts. We provide theoretical guarantees that our loss function is uniquely optimized by the ground truth under specific conditions. Extensive experiments demonstrate TopInG's effectiveness in tackling key challenges, such as handling variform rationale subgraphs, balancing predictive performance with interpretability, and mitigating spurious correlations. Results show that our approach improves upon state-of-the-art methods on both predictive accuracy and interpretation quality.