mlsanityData to 7 Oct 2026

Distill n' Explain: explaining graph neural networks using simple surrogates

arXiv 2303.10139 ↗First posted 17 Mar 2023cs.LG cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Explaining node predictions in graph neural networks (GNNs) often boils down to finding graph substructures that preserve predictions. Finding these structures usually implies back-propagating through the GNN, bonding the complexity (e.g., number of layers) of the GNN to the cost of explaining it. This naturally begs the question: Can we break this bond by explaining a simpler surrogate GNN? To answer the question, we propose Distill n' Explain (DnX). First, DnX learns a surrogate GNN via knowledge distillation. Then, DnX extracts node or edge-level explanations by solving a simple convex program. We also propose FastDnX, a faster version of DnX that leverages the linear decomposition of our surrogate model. Experiments show that DnX and FastDnX often outperform state-of-the-art GNN explainers while being orders of magnitude faster. Additionally, we support our empirical findings with theoretical results linking the quality of the surrogate model (i.e., distillation error) to the faithfulness of explanations.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

44 of 61 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  10. 2019Simplifying Graph Convolutional Networkscited by 1,470
  11. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  12. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
32 more
  1. 2020Simple and Deep Graph Convolutional Networkscited by 857
  2. 2015Gated Graph Sequence Neural Networkscited by 792
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  4. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  5. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  6. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  7. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  8. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  9. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  10. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  11. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 199
  12. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  13. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  14. 2022Dataset Distillation using Neural Feature Regressioncited by 177
  15. 2019Ensemble Distribution Distillationcited by 158
  16. 2020Cross-Layer Distillation with Semantic Calibrationcited by 141
  17. 2017On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learningcited by 136
  18. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  19. 2020Distilling Knowledge from Graph Convolutional Networkscited by 128
  20. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  21. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  22. 2020Drug discovery with explainable artificial intelligencecited by 118
  23. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  24. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  25. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  26. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  27. 2021On Representation Knowledge Distillation for Graph Neural Networkscited by 38
  28. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  29. 2022OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networkscited by 33
  30. 2022Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentationcited by 28
  31. 2021Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targetscited by 19
  32. 2020Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networkscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 5; 2026: 5.

18 papers.

Sort:

By area:

  1. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  2. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  3. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 8
  4. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  5. 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Timecited by 5
  6. 2024Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpointcited by 5
  7. 2024Game-theoretic Counterfactual Explanation for Graph Neural Networkscited by 2
  8. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  9. 2026Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalizationcited by 2
  10. 2024On the Feasibility of Fidelity^- for Graph Pruningcited by 1
  11. 2025Interpretability of Graph Neural Networks to Assess Effects of Global Change Drivers on Ecological Networkscited by 1
  12. 2026Interpretable Analytic Calabi-Yau Metrics via Symbolic Distillationcited by 1
6 more
  1. 2024GNNAnatomy: Rethinking Model-Level Explanations for Graph Neural Networkscited by 0
  2. 2025DistShap: Scalable GNN Explanations with Distributed Shapley Valuescited by 0
  3. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  4. 2026CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networkscited by 0
  5. 2026Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Ballscited by 0
  6. 2026From Abductive Explanations to Global Logical Rules for Node Classification in SGCscited by 0