Research map / Label-efficient and robust learning / Semi-supervised learning
Exploiting Unlabeled Data via Partial Label Assignment for Multi-Class Semi-Supervised Learning
Zhen-Ru Zhang, Qian-Wen Zhang, Yunbo Cao, Min-Ling Zhang
This paper tried a common change: Train longer
Increase the number of training iterations · Segment · labeling confidence difference between adjacent iterations No clear effect
What 387 accepted papers report for this change
- 211 improved
- 62 no clear effect
- 30 mixed
- 84 hurt
- Lightweight Federated Incremental Learning via Decoupled Replay ICML 2026 · increase local training epochs from 5 to 40 · CIFAR10 (α=1.0) · test accuracyImproved
- When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression ICML 2026 · train longer on the full path search space (overfitting stage) · SBM graph, 10 communities, pin=0.6 · accuracy: 1.0 -> 0.98Hurt
- Causes and Consequences of Representational Similarity in Machine Learning Models ICML 2026 · train longer on LLM continued pretraining to test insufficient adaptation · perplexity across overlap settings · perplexityImproved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 |
|---|---|---|---|
| Use partial-label assignment and iterative communication between labeled-data and partial-label classifiers | EUPAL · 13 benchmark data sets, p = 0.5% | accuracy | Mixed |
| Use partial-label assignment and iterative communication between labeled-data and partial-label classifiers | EUPAL · 13 benchmark data sets, p = 1% | accuracy | Mixed |
| Use partial-label assignment and iterative communication between labeled-data and partial-label classifiers | EUPAL · 13 benchmark data sets, p = 5% | accuracy | Mixed |
| Increase the fraction of labeled training examples | EUPAL · Ecoli, Yeast, Wireless | accuracy | Improved |
| Vary the kNN neighborhood size and balancing parameter α (ablation) | EUPAL · Segment | accuracy | No clear effect |
| Increase the number of training iterations (ablation) | EUPAL · Segment | labeling confidence difference between adjacent iterations | No clear effect |
| Iteratively update candidate label sets using classifier predictions (ablation) | EUPAL · Ecoli, Wireless, Pen | transductive accuracy | Improved |
Closest papers by meaning
- Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization (NeurIPS 2020 · similarity 0.90)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.89)
- SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification (CVPR 2021 · similarity 0.89)
- Improved Generalization in Semi-Supervised Learning: A Survey of Theoretical Results (TPAMI 2022 · similarity 0.89)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.88)
- Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data (AAAI 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.
