Research map / Label-efficient and robust learning / Recognition and long-tail
Learning from Label Proportions: A Mutual Contamination Framework
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 |
|---|---|---|---|
| Use LMMCM instead of InvCal | LLP classification · Adult, LP [0, 1/2], bag size 512 | AUC: 0.7256 $\pm$ 0.0159 -> 0.8674 $\pm$ 0.0040 | Helped |
| Use LMMCM instead of InvCal | LLP classification · Adult, LP [1/2, 1], bag size 512 | AUC: 0.7480 $\pm$ 0.0500 -> 0.8500 $\pm$ 0.0186 | Helped |
| Use LMMCM instead of InvCal | LLP classification · MAGIC, LP [0, 1/2], bag size 512 | AUC: 0.8133 $\pm$ 0.0109 -> 0.8734 $\pm$ 0.0092 | Helped |
| Use LMMCM instead of InvCal | LLP classification · MAGIC, LP [1/2, 1], bag size 512 | AUC: 0.8215 $\pm$ 0.0136 -> 0.8567 $\pm$ 0.0292 | Helped |
| Use LMMCM instead of InvCal | LLP classification · Adult, LP [0, 1/2], bag sizes 8, 32, 128 | AUC: 0.8720 $\pm$ 0.0035 -> 0.8728 $\pm$ 0.0019; 0.8672 $\pm$ 0.0067 -> 0.8693 $\pm$ 0.0047; 0.8537 $\pm$ 0.0101 -> 0.8669 $\ | Mixed |
| Use LMMCM instead of InvCal | LLP classification · Adult, LP [1/2, 1], bag sizes 32, 128 | AUC: 0.8598 $\pm$ 0.0073 -> 0.8644 $\pm$ 0.0052; 0.8284 $\pm$ 0.0093 -> 0.8601 $\pm$ 0.0045 | Helped |
| Use LMMCM instead of InvCal | LLP classification · MAGIC, LP [0, 1/2], bag sizes 32, 128 | AUC: 0.8574 $\pm$ 0.0079 -> 0.8799 $\pm$ 0.0113; 0.8295 $\pm$ 0.0139 -> 0.8753 $\pm$ 0.0157 | Helped |
| Use LMMCM instead of InvCal | LLP classification · MAGIC, LP [1/2, 1], bag sizes 32, 128 | AUC: 0.8612 $\pm$ 0.0056 -> 0.8790 $\pm$ 0.0091; 0.8180 $\pm$ 0.0092 -> 0.8684 $\pm$ 0.0046 | Helped |
| Use LMMCM instead of InvCal | LLP classification · MAGIC, LP [0, 1/2], bag size 8 | AUC: 0.8918 $\pm$ 0.0076 -> 0.8909 $\pm$ 0.0077 | Hurt |
| Use LMMCM instead of InvCal | LLP classification · MAGIC, LP [1/2, 1], bag size 8 | AUC: 0.8936 $\pm$ 0.0066 -> 0.8911 $\pm$ 0.0083 | Hurt |
| Use LMMCM instead of InvCal | LLP classification · Adult, LP [1/2, 1], bag size 8 | AUC: 0.8680 $\pm$ 0.0021 -> 0.8584 $\pm$ 0.0164 | Hurt |
| Increase bag size | LMMCM · Adult and MAGIC, both LP distributions | AUC | No clear effect |
Closest papers by meaning
- Rethinking Learning from Label Proportions via Moment Matching (NeurIPS 2026 · similarity 0.91)
- Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation (ICLR 2024 · similarity 0.89)
- Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions (CVPR 2025 · similarity 0.89)
- Nearly Optimal Sample Complexity for Learning with Label Proportions (ICML 2025 · similarity 0.89)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.88)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.88)
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.