mlsanityData to 14 Oct 2026

How Faithful are Self-Explainable GNNs?

arXiv 2308.15096 ↗First posted 29 Aug 2023cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Self-explainable deep neural networks are a recent class of models that can output ante-hoc local explanations that are faithful to the model's reasoning, and as such represent a step forward toward filling the gap between expressiveness and interpretability. Self-explainable graph neural networks (GNNs) aim at achieving the same in the context of graph data. This begs the question: do these models fulfill their implicit guarantees in terms of faithfulness? In this extended abstract, we analyze the faithfulness of several self-explainable GNNs using different measures of faithfulness, identify several limitations -- both in the models themselves and in the evaluation metrics -- and outline possible ways forward.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

31 of 39 references.

References · 31

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  4. 2020Concept Bottleneck Modelscited by 1,032
  5. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  7. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  10. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  11. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  12. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
19 more
  1. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  2. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  3. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  4. 2015The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classificationcited by 76
  5. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  6. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  7. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  8. 2022Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Offcited by 61
  9. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
  10. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 53
  11. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  12. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  13. 2021Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systemscited by 36
  14. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
  15. 2023A Survey on Explainability of Graph Neural Networkscited by 29
  16. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  17. 2022Concept Embedding Analysis: A Reviewcited by 20
  18. 2022Towards Prototype-Based Self-Explainable Graph Neural Networkcited by 14
  19. 2020Graph Neural Networks Including Sparse Interpretabilitycited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 2.

5 papers.

  1. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 16
  2. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 11
  3. 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
  4. 2026GNN Explanations that do not Explain and How to find Themcited by 5
  5. 2026Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attributioncited by 0