Research map / Graph learning / GNN architectures

On Logic-based Self-Explainable Graph Neural Networks

NeurIPS 2025 · Graph learning › GNN architectures · approach: GNN explainability · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a logic-based self-explainable GNN, using logical rules as part of the model so its predictions come with built-in explanations.

Problem

Explaining GNN decisions is hard; most existing XAI methods for GNNs identify influential nodes or subgraphs, which the abstract frames as insufficient for explaining relational patterns.

Approach

Self-explainable GNN whose decisions are grounded in logic-based rules, so explanations are intrinsic to the model rather than post-hoc. Details beyond the abstract are not stated here.

Closest papers by meaning

• GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules (NeurIPS 2024 · similarity 0.90)
• Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective (ICML 2025 · similarity 0.90)
• Self-Interpretable Graph Learning with Sufficient and Necessary Explanations (AAAI 2024 · similarity 0.89)
• Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks (ICML 2024 · similarity 0.88)
• Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks (ICLR 2024 · similarity 0.88)
• Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning (AAAI 2025 · similarity 0.88)