mlsanityData to 7 Oct 2026

LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks

arXiv 2503.19476 ↗First posted 25 Mar 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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. To this end, we propose LogicXGNN, a post-hoc framework that constructs logical rules over reliable predicates explicitly designed to capture the GNN's message-passing structure, thereby ensuring effective grounding. We further introduce data-grounded fidelity (textitFidD), a realistic metric that evaluates explanations in their final-graph form, along with complementary utility metrics such as coverage and validity. Across extensive experiments, LogicXGNN improves textitFidD by over 20% on average relative to state-of-the-art methods while being 10-100 × faster. With strong scalability and utility performance, LogicXGNN produces explanations that are faithful to the model's logic and reliably grounded in observable data. Our code is available at https://github.com/allengeng123/LogicXGNN/.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 25 Mar 2025.

Builds on

24 of 43 references.

References · 24

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  6. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  7. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  8. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  9. 2016The Mythos of Model Interpretabilitycited by 716
  10. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  11. 2020A Survey on Neural Network Interpretabilitycited by 291
  12. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
12 more
  1. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  2. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  3. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  4. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 78
  5. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  6. 2019Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanationscited by 71
  7. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  8. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  9. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
  10. 2020xFraud: Explainable Fraud Transaction Detectioncited by 27
  11. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  12. 2024MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generationcited by 7

Built on by

Not cited yet.