Research map / Label-efficient and robust learning / Recognition and long-tail
Teaching-to-Learn and Learning-to-Teach for Multi-label Propagation
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 |
|---|---|---|---|
| add teaching-to-learn simple-to-difficult selection (vs random curriculum) (ablation) | ML-TLLT · Emotions | ranking loss: 0.260 -> 0.255 | Helped |
| add label correlation term in example selection (ablation) | ML-TLLT · Emotions | ranking loss: 0.260 -> 0.255 | Helped |
| add learning-to-teach feedback (vs constant 0.5) (ablation) | ML-TLLT · Emotions | ranking loss: 0.261 -> 0.255 | Helped |
| add teaching-to-learn selection (vs random) (ablation) | ML-TLLT · Emotions | Micro F1: 0.536 -> 0.540 | Helped |
| add label correlation term (ablation) | ML-TLLT · Emotions | Micro F1: 0.537 -> 0.540 | Helped |
| add learning-to-teach feedback (ablation) | ML-TLLT · Emotions | average precision: 0.713 -> 0.717 | Helped |
| ML-TLLT curriculum propagation instead of plain TRAM learner | TRAM · Corel5K | ranking loss: 0.297 -> 0.271 | Helped |
| ML-TLLT curriculum propagation instead of plain TRAM learner | TRAM · Emotions | Micro F1: 0.513 -> 0.540 | Helped |
| ML-TLLT curriculum propagation instead of plain TRAM learner | TRAM · Scene | average precision: 0.858 -> 0.859 | No clear effect |
| ML-TLLT curriculum propagation instead of plain TRAM learner | TRAM · Bibtex | Micro F1: 0.445 -> 0.476 | Helped |
Closest papers by meaning
- Knowledge Amalgamation for Multi-Label Classification via Label Dependency Transfer (AAAI 2023 · similarity 0.86)
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 2025 · similarity 0.83)
- Multi-Label Node Classification with Label Influence Propagation (ICLR 2025 · similarity 0.83)
- Predicting Label Distribution from Ternary Labels (NeurIPS 2024 · similarity 0.83)
- Calibrated Disambiguation for Partial Multi-label Learning (AAAI 2025 · similarity 0.83)
- TLLC: Transfer Learning-based Label Completion for Crowdsourcing (ICML 2025 · similarity 0.82)
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.