Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
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 L2X rather than the compared instancewise feature-selection methods | Synthetic nonlinear additive and feature-switching data · Synthetic data | median rank of influential features | Helped |
| Use L2X rather than the compared instancewise feature-selection methods | Synthetic XOR data · Synthetic XOR | median rank of influential features | Mixed |
| Use L2X rather than the compared instancewise feature-selection methods | Synthetic orange skin data · Synthetic orange skin | median rank of influential features | No clear effect |
Closest papers by meaning
- An Additive Instance-Wise Approach to Multi-class Model Interpretation (ICLR 2023 · similarity 0.91)
- Interpretability with full complexity by constraining feature information (ICLR 2023 · similarity 0.89)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.86)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.86)
- ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques (AAAI 2025 · similarity 0.86)
- Additive Models Explained: A Computational Complexity Approach (NeurIPS 2025 · 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.