Research map / Label-efficient and robust learning / Recognition and long-tail
A Deep Model With Local Surrogate Loss for General Cost-Sensitive Multi-Label Learning
Cheng-Yu Hsieh, Yi-An Lin, Hsuan-Tien Lin
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 |
|---|---|---|---|
| fine-tune with LLSL instead of BCE loss | BCE-trained deep model · Bibtex | normalised P@1: 0.4482 -> 0.3647 | Hurt |
| fine-tune with LLSL instead of BCE loss | BCE-trained deep model · Delicious | normalised P@3: 0.3778 -> 0.3581 | Hurt |
| fine-tune with LLSL instead of BCE loss | BCE-trained deep model · Wiki10-31K | normalised P@5: 0.3631 -> 0.3586 | Hurt |
| use LLSL instead of SLEEC | deep model · Bibtex | normalised P@3: 0.6036 -> 0.6157 | Improved |
| use LLSL instead of SLEEC | deep model · Delicious | normalised P@3: 0.3862 -> 0.3581 | Hurt |
| use weighted BCE instead of BCE | deep model · Example-F1 and Rank loss | relative ranking | Improved |
| use LLSL instead of weighted BCE | deep model · example-based criteria | relative ranking | Improved |
| use polynomial two-bit local approximator instead of linear one-bit (ablation) | LLSL · Example-F1, Micro-F1, Macro-F1 | relative ranking | Improved |
| use linear one-bit local approximator instead of more complex ones (ablation) | LLSL · Hamming loss and Rank loss | relative ranking | Improved |
| mix BCE (Hamming) loss with learned surrogate for Precision-at-k (ablation) | LLSL · many-label datasets | convergence | Improved |
Closest papers by meaning
- Multi-Label Learning with Stronger Consistency Guarantees (NeurIPS 2024 · similarity 0.87)
- A no-regret generalization of hierarchical softmax to extreme multi-label classification (NeurIPS 2018 · similarity 0.86)
- Noisy Label Learning With Provable Consistency for a Wider Family of Losses (TPAMI 2023 · similarity 0.86)
- Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations (AAAI 2025 · similarity 0.85)
- Neural Collapse in Multi-label Learning with Pick-all-label Loss (ICML 2024 · similarity 0.84)
- Towards Calibrated Multi-label Deep Neural Networks (CVPR 2024 · 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.
