Research map / Probabilistic and scientific modeling / Causal discovery
Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions
Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Ziwei Yang, Zheyang Li, Quanshi Zhang
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 |
|---|---|---|---|
| evaluate reformulated Taylor-interaction attributions on exact second-order polynomial models instead of sigmoid MLPs | Integrated Gradients · MNIST | fitting error E: 0.82% -> 0.12% | Mixed |
| evaluate on Sigmoid-MLP rather than Polynomial model | Occlusion-1 · MNIST | fitting error E: 0 -> 2.46% | Hurt |
| evaluate on Sigmoid-MLP rather than Polynomial model | Shapley value · MNIST | fitting error E: 0 -> 1.18% | Hurt |
Closest papers by meaning
- How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations (ICLR 2025 · similarity 0.89)
- quanda: An Interpretability Toolkit for Training Data Attribution Evaluation (NeurIPS 2026 · similarity 0.86)
- $\texttt{dattri}$: A Library for Efficient Data Attribution (NeurIPS 2024 · similarity 0.86)
- Iterative Search Attribution for Deep Neural Networks (ICML 2024 · similarity 0.86)
- Benchmarking the Attribution Quality of Vision Models (NeurIPS 2024 · similarity 0.86)
- Provably Better Explanations with Optimized Aggregation of Feature Attributions (ICML 2024 · 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.
