Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.05370 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913502989385728 |
|---|---|
| author | Li, Zeju Zheng, Ying-Qiu Chen, Chen Jbabdi, Saad |
| author_facet | Li, Zeju Zheng, Ying-Qiu Chen, Chen Jbabdi, Saad |
| contents | Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these pseudo-labels can further amplify this bias. Here we investigate pseudo-labeling strategies for imbalanced SSL including pseudo-label refinement and threshold adjustment, through the lens of statistical analysis. We find that existing SSL algorithms which generate pseudo-labels using heuristic strategies or uncalibrated model confidence are unreliable when imbalanced class distributions bias pseudo-labels. To address this, we introduce SEmi-supervised learning with pseudo-label optimization based on VALidation data (SEVAL) to enhance the quality of pseudo-labelling for imbalanced SSL. We propose to learn refinement and thresholding parameters from a partition of the training dataset in a class-balanced way. SEVAL adapts to specific tasks with improved pseudo-labels accuracy and ensures pseudo-labels correctness on a per-class basis. Our experiments show that SEVAL surpasses state-of-the-art SSL methods, delivering more accurate and effective pseudo-labels in various imbalanced SSL situations. SEVAL, with its simplicity and flexibility, can enhance various SSL techniques effectively. The code is publicly available (https://github.com/ZerojumpLine/SEVAL). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05370 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Label Refinement and Threshold Adjustment for Imbalanced Semi-Supervised Learning Li, Zeju Zheng, Ying-Qiu Chen, Chen Jbabdi, Saad Machine Learning Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these pseudo-labels can further amplify this bias. Here we investigate pseudo-labeling strategies for imbalanced SSL including pseudo-label refinement and threshold adjustment, through the lens of statistical analysis. We find that existing SSL algorithms which generate pseudo-labels using heuristic strategies or uncalibrated model confidence are unreliable when imbalanced class distributions bias pseudo-labels. To address this, we introduce SEmi-supervised learning with pseudo-label optimization based on VALidation data (SEVAL) to enhance the quality of pseudo-labelling for imbalanced SSL. We propose to learn refinement and thresholding parameters from a partition of the training dataset in a class-balanced way. SEVAL adapts to specific tasks with improved pseudo-labels accuracy and ensures pseudo-labels correctness on a per-class basis. Our experiments show that SEVAL surpasses state-of-the-art SSL methods, delivering more accurate and effective pseudo-labels in various imbalanced SSL situations. SEVAL, with its simplicity and flexibility, can enhance various SSL techniques effectively. The code is publicly available (https://github.com/ZerojumpLine/SEVAL). |
| title | Learning Label Refinement and Threshold Adjustment for Imbalanced Semi-Supervised Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.05370 |