mlsanityData to 7 Oct 2026

Generative Causal Explanations for Graph Neural Networks

arXiv 2104.06643 ↗First posted 14 Apr 2021cs.LGcited by 124

Not on the map. Why?

Abstract (arXiv)

This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, Gem explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the graph learning tasks. In addition, Gem, once trained, can be used to explain the target GNN very quickly. Our theoretical analysis shows that several recent explainers fall into a unified framework of additive feature attribution methods. Experimental results on synthetic and real-world datasets show that Gem achieves a relative increase of the explanation accuracy by up to 30% and speeds up the explanation process by up to 110× as compared to its state-of-the-art alternatives.

Key facts. Cited by 124 papers in the map (data through 7 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

19 of 35 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Variational Graph Auto-Encoderscited by 1,373
  6. 2018Link Prediction Based on Graph Neural Networkscited by 829
  7. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  8. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  9. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  10. 2018Learning Deep Generative Models of Graphscited by 227
  11. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  12. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
7 more
  1. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  2. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  3. 2018Multi-Objective De Novo Drug Design with Conditional Graph Generative Modelcited by 101
  4. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  5. 2019Neural Network Attributions: A Causal Perspectivecited by 77
  6. 2018Explaining Deep Learning Models using Causal Inferencecited by 18
  7. 2020Towards Explainable Graph Representations in Digital Pathologycited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 33; 2023: 32; 2024: 25; 2025: 18; 2026: 8.

124 papers.

Sort:

By area:

  1. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  2. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  3. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  4. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  5. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  6. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 78
  7. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  8. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
  9. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  10. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  11. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  12. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
38 more
  1. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  2. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 34
  3. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  4. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  5. 2022OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networkscited by 33
  6. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  7. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  8. 2022Debiased Graph Neural Networks with Agnostic Label Selection Biascited by 25
  9. 2023PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Predictioncited by 25
  10. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  11. 2022Causal Transportability for Visual Recognitioncited by 23
  12. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  13. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  14. 2022Task-Agnostic Graph Explanationscited by 20
  15. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  16. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 20
  17. 2024EXGC: Bridging Efficiency and Explainability in Graph Condensationcited by 20
  18. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
  19. 2021Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networkscited by 18
  20. 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
  21. 2024Causal Evaluation of Language Modelscited by 18
  22. 2024Graph Neural Network Explanations are Fragilecited by 18
  23. 2024CausalFormer: An Interpretable Transformer for Temporal Causal Discoverycited by 17
  24. 2023CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosiscited by 16
  25. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 16
  26. 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13
  27. 2023Knowledge Graph Completion with Counterfactual Augmentationcited by 13
  28. 2023Causality and Independence Enhancement for Biased Node Classificationcited by 13
  29. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  30. 2022Robust Causal Graph Representation Learning against Confounding Effectscited by 12
  31. 2024Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanationcited by 12
  32. 2022MotifExplainer: a Motif-based Graph Neural Network Explainercited by 11
  33. 2022On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approachcited by 11
  34. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  35. 2022Towards Explainable Motion Prediction using Heterogeneous Graph Representationscited by 10
  36. 2024GOAt: Explaining Graph Neural Networks via Graph Output Attributioncited by 10
  37. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  38. 2023Exploring Causal Learning through Graph Neural Networks: An In-depth Reviewcited by 8

50 most cited of 124 All 124 (JSON)