AI RESEARCH
LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks
arXiv CS.LG
•
ArXi:2503.19476v5 Announce Type: replace Existing rule-based explanations for Graph Neural Networks (GNNs) provide global interpretability but often optimize and assess fidelity in an intermediate, uninterpretable concept space, overlooking grounding quality for end users in the final subgraph explanations. This gap yields explanations that may appear faithful yet be unreliable in practice.