Research map / Label-efficient and robust learning / Semi-supervised learning
Learning From Semi-Supervised Weak-Label Data
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 |
|---|---|---|---|
| add unlabeled data (SSWL vs SSWL-wo) (ablation) | SSWL · TMC, 60% missing labels | Micro-F1 | Helped |
| add unlabeled data (SSWL vs SSWL-wo) (ablation) | SSWL · Yeast, 60% missing labels | Micro-F1 | Helped |
| add unlabeled data (SSWL vs SSWL-wo) (ablation) | SSWL · msrc, 60% missing labels | Micro-F1 | Helped |
| add unlabeled data (SSWL vs SSWL-wo) (ablation) | SSWL · SceneImage, 60% missing labels | Micro-F1 | No clear effect |
| add unlabeled data (SSWL vs SSWL-wo) (ablation) | SSWL · TMC, 0% missing labels | Micro-F1 | No clear effect |
| add unlabeled data (SSWL vs SSWL-wo) (ablation) | SSWL · msrc, 0% missing labels | Micro-F1 | Helped |
| use SSWL weak-label handling instead of SSML | SSWL · TMC, 60% missing labels | Micro-F1 | Helped |
| use SSWL instead of SSML | SSWL · msrc, 0% missing labels | Micro-F1 | Hurt |
| use SSWL instead of Well-SVM | SSWL · SceneImage, 0% missing labels | Micro-F1 | Hurt |
| use SSWL instead of weak-label MLR-GL (no unlabeled data) | SSWL · Yeast, 60% missing labels | Micro-F1 | Helped |
| increase fraction of dropped observed labels from 0% to 60% | SSWL · TMC | Micro-F1 | Hurt |
Closest papers by meaning
- Robust Semi-Supervised Learning through Label Aggregation (AAAI 2016 · similarity 0.89)
- All Labels Are Not Created Equal: Enhancing Semi-Supervision via Label Grouping and Co-Training (CVPR 2021 · similarity 0.89)
- Label Propagation with Weak Supervision (ICLR 2023 · similarity 0.89)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.88)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.87)
- Learning from True-False Labels via Multi-modal Prompt Retrieving (ICML 2025 · similarity 0.87)
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.