Research map / Graph learning / GNN architectures
Generating In-Distribution Counterfactual Explanation for Graph Neural Networks
Linmao Chen, Chaobo He, Junwei Cheng, Chunying Li, Quanlong Guan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ICExplainer (diffusion with variational prior) instead of D4Explainer | counterfactual GNN explainers · Tree-Circles, Tree-Grid, BA-2motifs, MUTAG | validity: 0.905 -> 0.975 (Tree-Circles); 0.789 -> 0.937 (BA-2motifs) | Improved |
| use ICExplainer instead of leading baseline | counterfactual GNN explainers · four datasets | sparsity: 0.104 -> 0.049 (MUTAG); 0.096 (ProxyExplainer) vs 0.107 (ICE) on BA-2motifs | Mixed |
| use ICExplainer instead of D4Explainer | counterfactual GNN explainers · Tree-Circles, BA-2motifs, MUTAG | fidelity: 0.854 -> 0.913; 0.727 -> 0.843; 0.537 -> 0.630 | Improved |
| use ICExplainer instead of D4Explainer | counterfactual GNN explainers · Tree-Circles, Tree-Grid, BA-2motifs, MUTAG | MMD sum to original graphs: 0.1400 -> 0.0844; 0.1011 vs 0.0812; ProxyExplainer 0.0996 vs ICE 0.0812 on BA-2motifs | Mixed |
| use GCN encoder instead of SAGE (ablation) | ICExplainer · four datasets | validity: 0.961 -> 0.975 (Tree-Circles); 0.867 -> 0.937 (BA-2motifs) | Improved |
| use GCN encoder instead of GIN (ablation) | ICExplainer · four datasets | validity: 0.782 -> 0.843 (MUTAG); 0.954 -> 0.975 (Tree-Circles) | Improved |
| increase prediction loss weight lambda (ablation) | ICExplainer · Tree-Circles vs BA-2motifs | validity/fidelity | Mixed |
| increase number of PPGN layers L from 3 to 8 (ablation) | ICExplainer · Tree-Circles, BA-2motifs | performance | Improved |
| increase latent dimension D from 8 to 128 (ablation) | ICExplainer · four datasets | performance | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- D4Explainer — D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion (NeurIPS 2023) · better on 15 of 15 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- COMRECGC: Global Graph Counterfactual Explainer through Common Recourse (ICML 2025 · similarity 0.89)
- Robust Stochastic Graph Generator for Counterfactual Explanations (AAAI 2024 · similarity 0.89)
- UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models (ICLR 2024 · similarity 0.89)
- Graph Inverse Style Transfer for Counterfactual Explainability (ICML 2025 · similarity 0.89)
- Structure Your Data: Towards Semantic Graph Counterfactuals (ICML 2024 · similarity 0.88)
- GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
