mlsanityData to 7 Oct 2026

Contrastive Graph Neural Network Explanation

arXiv 2010.13663 ↗First posted 26 Oct 2020cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks achieve remarkable results on problems with structured data but come as black-box predictors. Transferring existing explanation techniques, such as occlusion, fails as even removing a single node or edge can lead to drastic changes in the graph. The resulting graphs can differ from all training examples, causing model confusion and wrong explanations. Thus, we argue that explicability must use graphs compliant with the distribution underlying the training data. We coin this property Distribution Compliant Explanation (DCE) and present a novel Contrastive GNN Explanation (CoGE) technique following this paradigm. An experimental study supports the efficacy of CoGE.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 8; 2023: 4; 2024: 0; 2025: 0; 2026: 1.

20 papers.

Sort:

  1. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  2. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  3. 2022Evaluating Explainability for Graph Neural Networkscited by 85
  4. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  5. 2021MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networkscited by 32
  6. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  7. 2021A Meta-Learning Approach for Training Explainable Graph Neural Networkscited by 15
  8. 2022Differentially Private Graph Classification with GNNscited by 12
  9. 2021An Empirical Study: Extensive Deep Temporal Point Processcited by 10
  10. 2022Deconfounding to Explanation Evaluation in Graph Neural Networkscited by 10
  11. 2023GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanationscited by 9
  12. 2022Towards Training GNNs using Explanation Directed Message Passingcited by 7
8 more
  1. 2022DT+GNN: A Fully Explainable Graph Neural Network using Decision Treescited by 6
  2. 2022GRETEL: A unified framework for Graph Counterfactual Explanation Evaluationcited by 6
  3. 2021Self-learn to Explain Siamese Networks Robustlycited by 5
  4. 2022PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networkscited by 5
  5. 2023Structural Explanations for Graph Neural Networks using HSICcited by 4
  6. 2023Robust Ante-hoc Graph Explainer using Bilevel Optimizationcited by 4
  7. 2023Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapescited by 1
  8. 2026Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainabilitycited by 0