Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling
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 SESM instead of ProSeNet | MIT-BIH · MIT-BIH | AOPC: 0.186 -> 0.232 | Helped |
| Use SESM instead of the strongest listed baseline | PDB · PDB | AOPC: 0.130 -> 0.135 | Helped |
| Use SESM instead of SelfExplain | YelpP · YelpP | AOPC: 0.379 -> 0.480 | Helped |
| Use SESM instead of SelfExplain | YelpF · YelpF | AOPC: 0.268 -> 0.336 | Helped |
| Use SESM instead of SelfExplain | SNLI · SNLI | AOPC: 0.287 -> 0.412 | Helped |
| Train with class weights (ablation) | SESM · MIT-BIH | accuracy: 0.982 -> 0.987 | Helped |
| Train with class weights (ablation) | SESM · MIT-BIH | Avg.R: 0.893 -> 0.921 | Helped |
| Train with class weights (ablation) | SESM · MIT-BIH | AOPC: 0.232 -> 0.230 | No clear effect |
| Train with class weights (ablation) | SESM · PDB | AOPC: 0.135 -> 0.153 | Helped |
| Train with class weights (ablation) | SESM · PDB | Avg.R: 0.333 -> 0.317 | Hurt |
| Increase the number of heads to 8 (ablation) | SESM · MIT-BIH | performance | Helped |
| Increase the number of heads to 16 (ablation) | SESM · PDB | performance | Helped |
Closest papers by meaning
- Pantypes: Diverse Representatives for Self-Explainable Models (AAAI 2024 · similarity 0.86)
- Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning (AAAI 2024 · similarity 0.85)
- MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes (CVPR 2024 · similarity 0.85)
- BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation (AAAI 2025 · similarity 0.85)
- Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference (AAAI 2025 · similarity 0.84)
- Interpretable Image Classification via Non-parametric Part Prototype Learning (CVPR 2025 · similarity 0.84)
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.