Research map / Label-efficient and robust learning / Recognition and long-tail
Learning with Feature Network and Label Network Simultaneously
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 label network to feature network (DRML vs DRML (By = I)) (ablation) | DRML · Medical | F1: 0.3532 -> 0.3798 | Helped |
| add label network to feature network (DRML vs DRML (By = I)) (ablation) | DRML · Bookmarks | F1: 0.2029 -> 0.2534 | Helped |
| add label network to feature network (DRML vs DRML (By = I)) (ablation) | DRML · Yeast | F1: 0.4441 -> 0.4843 | Helped |
| learned feature network (DRML (By = I)) instead of graph Laplacian (FGL) | DRML (By = I) · Medical | F1: 0.2937 -> 0.3532 | Helped |
| learned feature network (DRML (By = I)) instead of graph Laplacian (FGL) | DRML (By = I) · Yeast | F1: 0.4420 -> 0.4441 | No clear effect |
| DRML instead of FastTag+FGL | DRML · Bookmarks | F1: 0.2226 -> 0.2534 | Helped |
| DRML instead of LEML | DRML · Yeast | F1: 0.4685 -> 0.4843 | Helped |
| graph Laplacian feature regularization (FGL) over LeastSquares | LeastSquares · Medical | F1: 0.2922 -> 0.2937 | No clear effect |
| add FGL regularization to FastTag | FastTag · Medical | F1: 0.3228 -> 0.3427 | Helped |
| raise feature dropout level p from 0 initially | DRML · Medical, Bookmarks, Yeast | F1 | Helped |
| continue increasing dropout level beyond optimum | DRML · Medical, Bookmarks, Yeast | F1 | Hurt |
| DRML at 20% observed label rate vs FGL and FastTag | DRML · Medical | F1: about 4% gain | Helped |
Closest papers by meaning
- Generalization Analysis for Multi-Label Learning (ICML 2024 · similarity 0.87)
- Limited-Supervised Multi-Label Learning with Dependency Noise (AAAI 2024 · similarity 0.86)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.85)
- Double-Layer Hybrid-Label Identification Feature Selection for Multi-View Multi-Label Learning (AAAI 2024 · similarity 0.85)
- T-MDML: Triplet-based Multiple Distance Metric Learning for Multi-Instance Multi-Label Classification with Label Correlation (AAAI 2025 · similarity 0.85)
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 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.