Research map / Graph learning / Graph self-supervised learning
Quantifying Explainers of Graph Neural Networks in Computational Pathology
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GnnExplainer rather than GraphGrad-CAM++ | GIN cell-graph explanations · BRACS | maximum separability (without risk): 9.09 -> 12.98 | Helped |
| Use GnnExplainer rather than GraphGrad-CAM++ | GIN cell-graph explanations · BRACS | average separability (without risk): 5.85 -> 6.25 | Helped |
| Use GraphGrad-CAM++ rather than GnnExplainer | GIN cell-graph explanations · BRACS | correlated separability (without risk): 0.72 -> 1.16 | Helped |
| Use GraphGrad-CAM++ rather than GraphGrad-CAM | GIN cell-graph explanations · BRACS | correlated separability (without risk): 1.14 -> 1.16 | Helped |
| Use GraphGrad-CAM++ rather than GraphGrad-CAM | GIN cell-graph explanations · BRACS | average separability (without risk): 5.80 -> 5.85 | No clear effect |
| Use any studied graph explainer rather than random nucleus selection | GIN cell-graph explanations · BRACS | average separability (without risk): Random: 3.00; GnnExplainer: 6.25; GraphGrad-CAM: 5.80; GraphGrad-CAM++: 5.85; GraphLRP: 4.44 | Helped |
| Use GraphLRP rather than GraphGrad-CAM++ | GIN cell-graph explanations · BRACS | correlated separability (without risk): 1.16 -> -0.87 | Hurt |
| Select nuclei by explainer importance rather than randomly | BRACS cell-graph explanations · BRACS | average separability: Random: 3.00; GnnExplainer: 6.25; GraphGrad-CAM: 5.80; GraphGrad-CAM++: 5.85; GraphLRP: 4.44 | Helped |
Closest papers by meaning
- Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology (NeurIPS 2026 · similarity 0.86)
- BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathology (CVPR 2025 · similarity 0.85)
- Dynamic Entity-Masked Graph Diffusion Model for Histopathology Image Representation Learning (AAAI 2025 · similarity 0.85)
- xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology (NeurIPS 2024 · similarity 0.84)
- Cell Graph Transformer for Nuclei Classification (AAAI 2024 · similarity 0.84)
- Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis (CVPR 2024 · similarity 0.83)
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.