Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Xin, Cheng, Xu, Fan, Ding, Xin, Gao, Jie, Ding, Jiaxin
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
Awards: G1490444338, Collaborative Research: PPoSS: LARGE: Principles and Infrastructure of Extreme Scale Edge Learning for Computational Screening and Surveillance for Health Care, Unravel machine learning blackboxes -- A general, effective and performance-guaranteed statistical framework for complex and irregular inference problems in data science, ATD: Algorithms and Geometric Methods for Community and Anomaly Detection and Robust Learning in Complex Networks, Collaborative Research: AF: Small: Promoting Social Learning Amid Interference in the Age of Social Media, CRCNS Research Proposal: Modeling Human Brain Development as a Dynamic Multi-Scale Network Optimization Process
OpenAlex ID: W4414973395
Cites:
Cited by:
Related to: