Research map / Label-efficient and robust learning / Recognition and long-tail
Model Agnostic Supervised Local Explanations
Read the paperCheck 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 MAPLE + RF instead of RF | RF regression · Autompgs | RMSE: 0.4164 -> 0.381 | Helped |
| Use MAPLE + RF instead of RF | RF regression · Communities | RMSE: 0.745 -> 0.688 | Helped |
| Use MAPLE + RF instead of RF | RF regression · Crimes | RMSE: 1.012 -> 0.331 | Helped |
| Use MAPLE + RF instead of RF | RF regression · Music | RMSE: 0.742 -> 0.764 | Hurt |
| Use MAPLE + GBRT instead of GBRT | GBRT regression · Crimes | RMSE: 0.968 -> 0.295 | Helped |
| Use MAPLE + GBRT instead of GBRT | GBRT regression · Music | RMSE: 0.658 -> 0.849 | Hurt |
| Use MAPLE local explanations instead of LIME | MAPLE predictions, causal explanation evaluation · Autompgs | causal RMSE: 0.178 -> 0.042 | Helped |
| Use MAPLE local explanations instead of LIME | MAPLE predictions, causal explanation evaluation · Communities | causal RMSE: 0.409 -> 0.130 | Helped |
| Use MAPLE local explanations instead of LIME | MAPLE predictions, causal explanation evaluation · Crimes | causal RMSE: 0.276 -> 0.047 | Helped |
| Use MAPLE as a black-box explainer instead of LIME | SVR predictions · Autompgs | causal RMSE: 0.282 -> 0.15 | Helped |
| Use MAPLE as a black-box explainer instead of LIME | SVR predictions · Crimes | causal RMSE: 0.183 vs 0.232 | No clear effect |
| Increase neighborhood scale to σ = 0.25 rather than σ = 0.1 | MAPLE vs LIME black-box explanations · Communities, Crimes, and Music | causal RMSE | Hurt |
Closest papers by meaning
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.88)
- An Additive Instance-Wise Approach to Multi-class Model Interpretation (ICLR 2023 · similarity 0.88)
- Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning (NeurIPS 2023 · similarity 0.88)
- Learning Global Transparent Models consistent with Local Contrastive Explanations (NeurIPS 2020 · similarity 0.87)
- Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again (NeurIPS 2026 · similarity 0.85)
- Self-Interpretable Graph Learning with Sufficient and Necessary Explanations (AAAI 2024 · similarity 0.85)
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.