Research map / Learning theory and algorithms / Prediction and decision losses
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data
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 L-Shapley instead of the comparison methods for feature ranking | Word-CNN · IMDB Review | log-odds decrease after masking top-ranked words | Helped |
| Use L-Shapley or C-Shapley instead of the comparison methods for feature ranking | Char-CNN · AG's News | log-odds decrease after masking top-ranked words | Helped |
| Use C-Shapley instead of the comparison methods for feature ranking | LSTM · Yahoo! Answers | log-odds decrease after masking top-ranked words | Helped |
| Use L-Shapley with order 1, SampleShapley, or KernelSHAP instead of C-Shapley | LSTM · Yahoo! Answers | log-odds decrease after masking top-ranked words | Hurt |
| Use C-Shapley instead of the comparison methods for feature ranking | CNN · MNIST | log-odds decrease after masking top-ranked pixels | Helped |
| Use C-Shapley instead of the comparison methods for feature ranking | AlexNet-modified CNN · CIFAR10 | log-odds decrease after masking top-ranked pixels | Helped |
| Use L-Shapley with order 1 instead of C-Shapley | Text classifiers · Yahoo! Answers | log-odds decrease after masking top-ranked words | Hurt |
Closest papers by meaning
- Shapley Residuals: Quantifying the limits of the Shapley value for explanations (NeurIPS 2021 · similarity 0.91)
- shapiq: Shapley Interactions for Machine Learning (NeurIPS 2024 · similarity 0.88)
- RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank (ICLR 2025 · similarity 0.88)
- Unlocking the Game: Estimating Games in Möbius Representation for Explanation and High-Order Interaction Detection (AAAI 2025 · similarity 0.87)
- Provably Accurate Shapley Value Estimation via Leverage Score Sampling (ICLR 2025 · similarity 0.86)
- A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values (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.