# Contrastive Graph Neural Network Explanation

arXiv: https://arxiv.org/abs/2010.13663 · HTML: https://mlsanity.com/paper/2010.13663/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Evaluating Explainability for Graph Neural Networks](https://mlsanity.com/paper/2208.09339/) (2022)
- [Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods](https://mlsanity.com/paper/2106.09078/) (2021)
- [MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks](https://mlsanity.com/paper/2104.08060/) (2021)
- [A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges](https://mlsanity.com/paper/2210.12089/) (2022)
- [A Meta-Learning Approach for Training Explainable Graph Neural Networks](https://mlsanity.com/paper/2109.09426/) (2021)
- [Differentially Private Graph Classification with GNNs](https://mlsanity.com/paper/2202.02575/) (2022)
- [An Empirical Study: Extensive Deep Temporal Point Process](https://mlsanity.com/paper/2110.09823/) (2021)
- [Deconfounding to Explanation Evaluation in Graph Neural Networks](https://mlsanity.com/paper/2201.08802/) (2022)
- [GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations](https://mlsanity.com/paper/2309.16223/) (2023)
- [Towards Training GNNs using Explanation Directed Message Passing](https://mlsanity.com/paper/2211.16731/) (2022)
- [DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees](https://mlsanity.com/paper/2205.13234/) (2022)
- [GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation](https://mlsanity.com/paper/2206.02957/) (2022)
- [Self-learn to Explain Siamese Networks Robustly](https://mlsanity.com/paper/2109.07371/) (2021)
- [PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks](https://mlsanity.com/paper/2210.17159/) (2022)
- [Structural Explanations for Graph Neural Networks using HSIC](https://mlsanity.com/paper/2302.02139/) (2023)
- [Robust Ante-hoc Graph Explainer using Bilevel Optimization](https://mlsanity.com/paper/2305.15745/) (2023)
- [Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes](https://mlsanity.com/paper/2308.02353/) (2023)
- [Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability](https://mlsanity.com/paper/2606.05756/) (2026)

## 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.