Research map / Graph learning / GNN architectures
FlowX: Towards Explainable Graph Neural Networks via Message Flows
Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao, Kang Li, Shuiwang Ji
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 |
|---|---|---|---|
| add necessity-oriented coalition-weight training (FlowX_nec) to FlowX sampling | FlowX · 9 datasets, GIN | Fidelity+ | Improved |
| add sufficiency-oriented coalition-weight training (FlowX_suf) to FlowX sampling | FlowX · 9 datasets, GIN | Fidelity- | Improved |
| use FlowX_suf instead of RC-Explainer | Graph-SST2 · Graph-SST2, GIN | Fidelity- | Hurt |
| train flow-level mask (FlowMask) instead of edge-level mask (GNNExplainer), same MI objective (ablation) | GNNExplainer · 9 datasets, necessary explanations (Fidelity+) | Fidelity+: better on 7 out of 9 datasets | Improved |
| train flow-level mask (FlowMask) instead of edge-level mask (GNNExplainer) (ablation) | GNNExplainer · 9 datasets, sufficient explanations (Fidelity-) | Fidelity-: better on 6 out of 9 datasets | Improved |
| use flow explanations instead of edge explanations (ablation) | explainers · BA-Traffic | full recall sparsity | Improved |
| use node-based explainers converted to edges instead of edge/flow ones | GradCAM, DeepLIFT · BA-Traffic | full recall sparsity | Hurt |
| learn coalition weights on top of sampled Shapley scores (ablation) | FlowX · explanation training | explanation quality | Improved |
Closest papers by meaning
- Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective (ICML 2025 · similarity 0.90)
- Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks (ICLR 2024 · similarity 0.90)
- Self-Interpretable Graph Learning with Sufficient and Necessary Explanations (AAAI 2024 · similarity 0.89)
- Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks (ICML 2024 · similarity 0.89)
- Factorized Explainer for Graph Neural Networks (AAAI 2024 · similarity 0.89)
- Stratified GNN Explanations through Sufficient Expansion (AAAI 2024 · similarity 0.89)
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.
