Research map / Label-efficient and robust learning / Semi-supervised learning
RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes RankMatch, a semi-supervised label distribution learning method that uses rank correlation between labels to generate pseudo-labels that preserve label ranking relationships.
Problem
Semi-supervised label distribution learning (SSLDL) is largely unexplored; existing pseudo-label SSL methods fail because their pseudo-labels match overall similarity to ground truth but do not preserve the ranking relationships among true labels.
Approach
Exploits rank correlation between labels to build pseudo-labels that preserve the relative ranking of label description degrees, rather than only overall similarity to ground truth.
Closest papers by meaning
- Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data (CVPR 2023 · similarity 0.91)
- All Labels Are Not Created Equal: Enhancing Semi-Supervision via Label Grouping and Co-Training (CVPR 2021 · similarity 0.90)
- LaSSL: Label-Guided Self-Training for Semi-supervised Learning (AAAI 2022 · similarity 0.90)
- Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning (NeurIPS 2023 · similarity 0.90)
- Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning (ICML 2024 · similarity 0.90)
- Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling (AAAI 2025 · similarity 0.89)
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.