Research map / Label-efficient and robust learning / Recognition and long-tail
How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions
Michael Tsang, Sirisha Rambhatla, Yan Liu
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 ArchAttribute instead of SOC | BERT · SST test set, word attribution | Word ρ: 0.768 -> 0.809 | Improved |
| Use ArchAttribute instead of SOC | BERT · SST test set, phrase attribution | Phrase ρ: 0.794 -> 0.836 | Improved |
| Use ArchAttribute instead of Integrated Gradients | ResNet152 · MS COCO dev set, image segments | Segment AUC: 0.786 -> 0.919 | Improved |
Closest papers by meaning
- Provably Better Explanations with Optimized Aggregation of Feature Attributions (ICML 2024 · similarity 0.84)
- Exploring the cloud of feature interaction scores in a Rashomon set (ICLR 2024 · similarity 0.84)
- Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables (NeurIPS 2024 · similarity 0.84)
- Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation (ICML 2024 · similarity 0.83)
- Regional Explanations: Bridging Local and Global Variable Importance (NeurIPS 2025 · similarity 0.83)
- On the Joint Interaction of Models, Data, and Features (ICLR 2024 · 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.
