Research map / Graph learning / Graph self-supervised learning
CLEAR: Generative Counterfactual Explanations on Graphs
Jing Ma, Ruocheng Guo, Saumitra Mishra, Aidong Zhang, Jundong Li
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 CLEAR instead of CF-GNNExplainer | graph CFE generator · Ogbg-molhiv | validity: 0.54 -> 0.98 | Improved |
| use CLEAR instead of best baseline on causality | graph CFE generator · Community | causality: 0.52 -> 0.65 | Improved |
| use CLEAR instead of MEG for generation time | graph CFE generator · Community | time (s): 27.29 -> 0.01 | Improved |
| CLEAR vs EG-RM on structure proximity | CLEAR · Ogbg-molhiv | Proximity_A: 0.96 -> 0.95 | Hurt |
| add auxiliary variable S (CLEAR vs CLEAR-VAE) (ablation) | CLEAR-VAE · Community, Ogbg-molhiv | causality | Improved |
| add counterfactual prediction loss (ablation) | CLEAR · Community, Ogbg-molhiv | validity | Improved |
| add similarity loss on graph structure and node features (ablation) | CLEAR · Community, Ogbg-molhiv | proximity | Improved |
| vary alpha and beta hyperparameters | CLEAR · Ogbg-molhiv | performance | No clear effect |
Closest papers by meaning
- Robust Stochastic Graph Generator for Counterfactual Explanations (AAAI 2024 · similarity 0.91)
- Graph Inverse Style Transfer for Counterfactual Explainability (ICML 2025 · similarity 0.91)
- Structure Your Data: Towards Semantic Graph Counterfactuals (ICML 2024 · similarity 0.90)
- UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models (ICLR 2024 · similarity 0.90)
- COMRECGC: Global Graph Counterfactual Explainer through Common Recourse (ICML 2025 · similarity 0.88)
- Counterfactual Maps: What They Are and How to Find Them (NeurIPS 2026 · 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.
