Research map / Graph learning / GNN architectures
V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs
Senzhang Wang, Jun Yin, Chaozhuo Li, Xing Xie, Jianxin Wang
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 V-InfoR instead of best baseline under 20% random noise | GNN explainers · Mutag | FNS: 0.2207 -> 0.2852 | Improved |
| Use V-InfoR instead of best baseline under 20% random noise | GNN explainers · BA-3Motifs | FNS: 0.4222 -> 0.4610 | Improved |
| Use V-InfoR instead of best baseline under 20% random noise | GNN explainers · Ogbg-molhiv | FNS: 0.2198 -> 0.2542 | Improved |
| Use V-InfoR instead of best baseline under 20% random noise | GNN explainers · Ogbg-ppa | FNS: 0.5200 -> 0.5680 | Improved |
| Use V-InfoR instead of best baseline under GRABNEL attack, 5% budget | GNN explainers · BA-3Motifs | FNS: 0.5582 -> 0.6157 | Improved |
| Use V-InfoR instead of best baseline under GRABNEL attack, 10% budget | GNN explainers · Mutag | FNS: 0.4904 -> 0.5427 | Improved |
| Raise GRABNEL attack budget from 5% to 10% | V-InfoR · Mutag | PN: 0.4588 -> 0.4277 | Mixed |
| Add noise ratio 0 to 0.30 sweep (no corruption) | V-InfoR · BA-3Motifs and Mutag | FNS | Improved |
| Remove the robust graph representation extractor (No-VAE) (ablation) | V-InfoR · BA-3Motifs, Mutag, etc. | PS/PN/FNS | Improved |
| Replace GIB objective with sparsity-driven MI objective (No-GIB) (ablation) | V-InfoR · all datasets | FNS | Improved |
| Remove both VAE extractor and GIB (No-VAE-GIB) (ablation) | V-InfoR · all datasets | FNS | Improved |
| Vary tau in [0.1, 0.5] | V-InfoR · BA-3Motifs and Mutag | FNS | Improved |
Later papers that compared with this method
1 later accepted paper reports V-InFoR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation Space (ICLR 2026 · better on 2 of 2 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
- Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks (ICLR 2024 · similarity 0.91)
- Factorized Explainer for Graph Neural Networks (AAAI 2024 · similarity 0.90)
- Higher Order Structures for Graph Explanations (AAAI 2025 · similarity 0.90)
- Self-Interpretable Graph Learning with Sufficient and Necessary Explanations (AAAI 2024 · similarity 0.90)
- Stratified GNN Explanations through Sufficient Expansion (AAAI 2024 · similarity 0.90)
- Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks (AAAI 2025 · similarity 0.90)
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.
