Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Compact Model for Large-Scale Multi-Label Data
Tong Wei, Yu-Feng Li
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 |
|---|---|---|---|
| apply POP label and feature parameter pruning to Binary Relevance | BR · wiki10 | model size: 23.50 GB -> 67.50 MB | Improved |
| apply POP pruning to BR | BR · eurlex | model size: 156.38 MB -> 20.18 MB | Improved |
| apply POP pruning to BR | BR · eurlex | PSP@1: 39.93 -> 40.06 | No clear effect |
| apply POP pruning to BR | BR · bibtex | PSP@5: 59.34 -> 58.86 | No clear effect |
| apply POP pruning to BR | BR · wiki10 | PSP@5: 13.96 -> 13.46 | No clear effect |
| add label parameter pruning before feature thresholding (POP vs DiSMEC feature-only pruning) (ablation) | POP · wiki10 | model size: 880.00 MB -> 67.50 MB | Improved |
| add label parameter pruning (POP vs DiSMEC) (ablation) | POP · eurlex | model size: 79.86 MB -> 20.18 MB | Improved |
| add label parameter pruning (POP vs DiSMEC) (ablation) | POP · eurlex | PSP@1: 41.20 -> 40.06 | No clear effect |
| increase tolerance epsilon (ablation) | POP · delicious, eurlex, wiki10 | P@k | Hurt |
| increase tolerance epsilon (ablation) | POP · delicious, eurlex, wiki10 | model size reduction | Improved |
| increase lambda too far (ablation) | POP · delicious, eurlex, wiki10 | P@k | Hurt |
Closest papers by meaning
- Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning (CVPR 2026 · similarity 0.88)
- Partial Multi-Label Learning via Large Margin Nearest Neighbour Embeddings (AAAI 2022 · similarity 0.88)
- Partial Multi-Label Learning by Low-Rank and Sparse Decomposition (AAAI 2019 · similarity 0.88)
- Generalization Analysis for Label-Specific Representation Learning (NeurIPS 2024 · similarity 0.87)
- Limited-Supervised Multi-Label Learning with Dependency Noise (AAAI 2024 · similarity 0.87)
- Enhancing Multi-Label Classification via Dynamic Label-Order Learning (AAAI 2024 · similarity 0.87)
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.
