Improving Multi-Label Contrastive Learning by Leveraging Label Distribution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913673148104704 |
|---|---|
| author | Chen, Ning Lyu, Shen-Huan Wu, Tian-Shuang Wang, Yanyan Tang, Bin |
| author_facet | Chen, Ning Lyu, Shen-Huan Wu, Tian-Shuang Wang, Yanyan Tang, Bin |
| contents | In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and negative samples based on the overlap between labels and used them for label-wise loss balancing. However, these methods suffer from a complex selection process and fail to account for the varying importance of different labels. To address these problems, we propose a novel method that improves multi-label contrastive learning through label distribution. Specifically, when selecting positive and negative samples, we only need to consider whether there is an intersection between labels. To model the relationships between labels, we introduce two methods to recover label distributions from logical labels, based on Radial Basis Function (RBF) and contrastive loss, respectively. We evaluate our method on nine widely used multi-label datasets, including image and vector datasets. The results demonstrate that our method outperforms state-of-the-art methods in six evaluation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Multi-Label Contrastive Learning by Leveraging Label Distribution Chen, Ning Lyu, Shen-Huan Wu, Tian-Shuang Wang, Yanyan Tang, Bin Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and negative samples based on the overlap between labels and used them for label-wise loss balancing. However, these methods suffer from a complex selection process and fail to account for the varying importance of different labels. To address these problems, we propose a novel method that improves multi-label contrastive learning through label distribution. Specifically, when selecting positive and negative samples, we only need to consider whether there is an intersection between labels. To model the relationships between labels, we introduce two methods to recover label distributions from logical labels, based on Radial Basis Function (RBF) and contrastive loss, respectively. We evaluate our method on nine widely used multi-label datasets, including image and vector datasets. The results demonstrate that our method outperforms state-of-the-art methods in six evaluation metrics. |
| title | Improving Multi-Label Contrastive Learning by Leveraging Label Distribution |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.19145 |