Research map / Label-efficient and robust learning / Recognition and long-tail
To Avoid the Pitfall of Missing Labels in Feature Selection: A Generative Model Gives the Answer
Yuanyuan Xu, Jun Wang, Jinmao Wei
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 |
|---|---|---|---|
| GMFS vs no feature selection (All-Fea) | GMFS · Emotions, 20% missing | MAP: 0.685±0.023 -> 0.732±0.019 | Improved |
| GMFS vs no feature selection (All-Fea) | GMFS · Delicious, 40% missing | MAP: 0.461±0.016 -> 0.514±0.017 | Improved |
| GMFS vs imputation-based MLMLFS | GMFS · Bibtex, 20% missing | MAP: 0.557±0.016 -> 0.578±0.008 | Improved |
| GMFS vs label embedding CMFS | GMFS · Delicious, 20% missing | MAP: 0.524±0.033 -> 0.547±0.013 | Improved |
| GMFS vs sparse method FSNM (cannot handle missing labels) | GMFS · Bibtex, 20% missing | MAP: 0.453±0.012 -> 0.578±0.008 | Improved |
| GMFS vs SFUS | GMFS · RCV1S1, 40% missing | MAP: 0.443±0.013 -> 0.512±0.009 | Improved |
| Increase missing label ratio from 20% to 40% | GMFS · Emotions | MAP: 0.732±0.019 -> 0.697±0.027 | Hurt |
| Increase missing label ratio from 20% to 40% | GMFS · Yeast | MAP: 0.775±0.007 -> 0.756±0.010 | Hurt |
| Replace spike-and-slab prior with Laplace prior (ablation) | GMFS · Emotions, 20% missing | MAP | Hurt |
| Increase selected features beyond 36 | GMFS · Emotions, 20% missing | MAP | Hurt |
| Set nearest neighbors k to 0 (no instance correlations) (ablation) | GMFS · Emotions, 20% missing | MAP | Hurt |
| Vary number of latent factors c from 2 to 40 | GMFS · Science, 20% missing | MAP | Mixed |
Closest papers by meaning
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 2025 · similarity 0.88)
- Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations (NeurIPS 2024 · similarity 0.87)
- Double-Layer Hybrid-Label Identification Feature Selection for Multi-View Multi-Label Learning (AAAI 2024 · similarity 0.87)
- Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · similarity 0.86)
- Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical (ICML 2024 · similarity 0.86)
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.86)
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.
