Research map / Label-efficient and robust learning / Recognition and long-tail
Complementary to Multiple Labels: A Correlation-Aware Correction Approach
Yi Dan Gao, Miao Xu, Min-Ling Zhang
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 |
|---|---|---|---|
| add correlation-based correction C of transition matrix (ablation) | MLCL · yeast (uniform complementary labels) | average precision: .472 -> .718 | Improved |
| add correction C (ablation) | MLCL · corel5k (uniform complementary labels) | average precision: .274 -> .391 | Improved |
| add correction C (ablation) | MLCL · scene (uniform complementary labels) | average precision: .671 -> .699 | Improved |
| add correction C (ablation) | MLCL · eurlex_dc (biased complementary labels) | hamming loss: .088 -> .109 | Hurt |
| add MSE regularizer (ablation) | MLCL · scene (uniform complementary labels) | average precision: .566 -> .699 | Improved |
| add MSE regularizer (ablation) | MLCL · eurlex_dc (uniform complementary labels) | average precision: .426 -> .549 | Improved |
| add MSE regularizer (ablation) | MLCL · yeast (uniform complementary labels) | average precision: .711 -> .718 | No clear effect |
| add MSE regularizer (ablation) | MLCL · corel5k (uniform complementary labels) | average precision: .389 -> .391 | No clear effect |
| increase beta from 0.1 to 1 (ablation) | MLCL · scene (uniform complementary labels) | average precision: .678 -> .699 | Improved |
| increase beta from 0.1 to 1 (ablation) | MLCL · bookmark (uniform complementary labels) | average precision: .565 -> .584 | Improved |
| increase beta from 0.1 to 1 (ablation) | MLCL · delicious (uniform complementary labels) | average precision: .554 -> .572 | No clear effect |
| add one relevant label per instance to complementary label | MLCL · scene | average precision: .699 -> .860 | Improved |
Closest papers by meaning
- Multi-Label Learning With Multiple Complementary Labels (TPAMI 2025 · similarity 0.93)
- Data Augmentation With Regularization for Multi-Labeled Complementary Label Learning (TPAMI 2025 · similarity 0.91)
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 2025 · similarity 0.90)
- Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical (ICML 2024 · similarity 0.89)
- Multi-Instance Multi-Label Classification from Crowdsourced Labels (AAAI 2025 · similarity 0.88)
- Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning (ICML 2024 · 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.
