Research map / Label-efficient and robust learning / Recognition and long-tail
Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models
Yi Sui, Ga Wu, Scott Sanner
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 |
|---|---|---|---|
| replace l2-regularized RPS with local Jacobian expansion | RPS · CIFAR-10 data debugging | correction rate: 3% better; 60 more mislabelled data identified | Improved |
| replace l2-regularized RPS with local Jacobian expansion | RPS · IMDB data debugging | correction rate: 1%; 35 more mislabelled data found | Improved |
| replace l2-regularized RPS with local Jacobian expansion | RPS · German Credit XGBoost | test accuracy | No clear effect |
| vary one-step gradient learning rate from 5e-4 to 1e-2 (ablation) | RPS-LJE · explanation stability | explanation consistency | No clear effect |
Closest papers by meaning
- Representer Point Selection for Explaining Deep Neural Networks (NeurIPS 2018 · similarity 0.89)
- Sample based Explanations via Generalized Representers (NeurIPS 2023 · similarity 0.86)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.83)
- Deep Regression Representation Learning with Topology (ICML 2024 · similarity 0.83)
- Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence (ICLR 2025 · similarity 0.83)
- Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations (ICML 2025 · 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.
