mlsanityData to 7 Oct 2026

L2XGNN: Learning to Explain Graph Neural Networks

arXiv 2209.14402 ↗First posted 28 Sep 2022cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs which provides faithful explanations by design. L2XGNN learns a mechanism for selecting explanatory subgraphs (motifs) which are exclusively used in the GNNs message-passing operations. L2XGNN is able to select, for each input graph, a subgraph with specific properties such as being sparse and connected. Imposing such constraints on the motifs often leads to more interpretable and effective explanations. Experiments on several datasets suggest that L2XGNN achieves the same classification accuracy as baseline methods using the entire input graph while ensuring that only the provided explanations are used to make predictions. Moreover, we show that L2XGNN is able to identify motifs responsible for the graph's properties it is intended to predict.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 40 of its 60 references that are in the map. First posted on arXiv 28 Sep 2022.

Builds on

40 of 60 references.

References · 40

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  8. 2019Self-Attention Graph Poolingcited by 421
  9. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  10. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  11. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  12. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
28 more
  1. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  2. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  3. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  4. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  5. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  6. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  7. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  8. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  9. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  10. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  11. 2021Implicit MLE: Backpropagating Through Discrete Exponential Family Distributionscited by 97
  12. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  13. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 78
  14. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  15. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63
  16. 2022Ordered Subgraph Aggregation Networkscited by 57
  17. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  18. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  19. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  20. 2021GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networkscited by 35
  21. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 34
  22. 2022OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networkscited by 33
  23. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  24. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
  25. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 20
  26. 2022MotifExplainer: a Motif-based Graph Neural Network Explainercited by 11
  27. 2022GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifscited by 6
  28. 2021Reliable Graph Neural Network Explanations Through Adversarial Trainingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 1; 2026: 4.

7 papers.

  1. 2023From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Modulecited by 19
  2. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 14
  3. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 10
  4. 2026Relevant Walk Search for Explaining Graph Neural Networkscited by 1
  5. 2026Combating Spurious Correlations in Graph Interpretability via Self-Reflectioncited by 0
  6. 2026Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hullscited by 0
  7. 2026A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networkscited by 0