04:00
2026-07-30
arxiv.org
artificial-intelligence
Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks
A new study from arXiv (2607.26344v1) reveals that gradient-based explainers for graph neural networks (GNNs) produce arbitrary top-k explanations when the input graph has automorphisms, such as chemi…