Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning with Declaratively Specified Entropy Constraints
Haitian Sun, William W. Cohen, Lidong Bing
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 the combined SSL constraints to DCE | DCE · Citeseer | accuracy (%): 63.6 -> 65.7 | Improved |
| Add the combined SSL constraints to DCE | DCE · Cora | accuracy (%): 60.7 -> 61.5 | Improved |
| Add the combined SSL constraints to DCE | DCE · PubMed | accuracy (%): 72.7 -> 74.4 | Improved |
| Add the combined SSL constraints (ablation) | DCE · Disease | F1: 30.4 -> 33.3 | Improved |
| Add the combined SSL constraints (ablation) | DCE · Drug | F1: 46.6 -> 50.1 | Improved |
| Add ER-Relation (ablation) | DCE · Disease | F1: 30.4 -> 31.4 | Improved |
| Add ER-Relation (ablation) | DCE · Drug | F1: 46.6 -> 48.5 | Improved |
| Add NBER-Doc (ablation) | DCE · Disease | F1: 30.4 -> 32.5 | Improved |
| Add NBER-Doc (ablation) | DCE · Drug | F1: 46.6 -> 48.2 | Improved |
| Add CT (ablation) | DCE · Disease | F1: 30.4 -> 31.2 | Improved |
| Add CT (ablation) | DCE · Drug | F1: 46.6 -> 49.8 | Improved |
| Add entropy regularization (ablation) | DCE · CiteSeer | accuracy (%): 59.8 -> 60.3 | Improved |
Closest papers by meaning
- Don’t fear the unlabelled: safe semi-supervised learning via debiasing (ICLR 2023 · similarity 0.87)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.85)
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 2024 · similarity 0.85)
- Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning (ICML 2024 · similarity 0.84)
- Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization (CVPR 2025 · similarity 0.84)
- A Unified Framework for Heterogeneous Semi-supervised Learning (CVPR 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.
