Research map / Label-efficient and robust learning / Recognition and long-tail
A Unified Approach to Interpreting Model Predictions
Scott M Lundberg, Su-In Lee
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 Kernel SHAP weighted regression instead of Shapley sampling values | Model-agnostic SHAP estimation · Dense and sparse decision tree models | model evaluations for similar approximation accuracy | Improved |
| Use Kernel SHAP instead of LIME | Local feature attribution · Dense and sparse decision tree models | consistency with local accuracy and consistency properties | Improved |
| Use SHAP values instead of LIME or DeepLIFT | Feature attribution · Sickness-score and max-allocation user studies | agreement with human explanations | Improved |
| Adapt DeepLIFT to use component-level SHAP values | Deep SHAP · Max-function attributions | consistency with human intuition | Improved |
| Use estimates closer to SHAP values instead of original DeepLIFT estimates | MNIST convolutional-network explanations · MNIST | change in log odds after masking pixels | Improved |
Closest papers by meaning
- InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly (ICLR 2025 · similarity 0.88)
- Additive Models Explained: A Computational Complexity Approach (NeurIPS 2025 · similarity 0.87)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.86)
- Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles (AAAI 2024 · similarity 0.86)
- SHAP values via sparse Fourier representation (NeurIPS 2025 · similarity 0.86)
- SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism (NeurIPS 2025 · similarity 0.86)
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.
