Huang, guangming and Long, Yunfei and Luo, Cunjin (2026) Similarity-Dissimilarity Loss for Multi-label Supervised Contrastive Learning. Transactions on Machine Learning Research.
Huang, guangming and Long, Yunfei and Luo, Cunjin (2026) Similarity-Dissimilarity Loss for Multi-label Supervised Contrastive Learning. Transactions on Machine Learning Research.
Huang, guangming and Long, Yunfei and Luo, Cunjin (2026) Similarity-Dissimilarity Loss for Multi-label Supervised Contrastive Learning. Transactions on Machine Learning Research.
Abstract
Supervised contrastive learning has achieved remarkable success by leveraging label information; however, determining positive samples in multi-label scenarios remains a critical challenge. In multi-label supervised contrastive learning (MSCL), multi-label relations are not yet fully defined, leading to ambiguity in identifying positive samples and formulating contrastive loss functions to construct the representation space. To address these challenges, we: (i) systematically formulate multi-label relations in MSCL, (ii) propose a novel Similarity-Dissimilarity Loss, which dynamically re-weights samples based on similarity and dissimilarity factors, (iii) further provide theoretically grounded proofs for our method through rigorous mathematical analysis that supports the formulation and effectiveness, and (iv) offer a unified form and paradigm for both single-label and multi-label supervised contrastive loss. We conduct experiments on both image and text modalities and further extend the evaluation to the medical domain. The results show that our method consistently outperforms baselines in comprehensive evaluations, demonstrating its effectiveness and robustness.
| Item Type: | Article |
|---|---|
| Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
| SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
| Depositing User: | Unnamed user with email elements@essex.ac.uk |
| Date Deposited: | 13 Nov 2026 15:09 |
| Last Modified: | 13 Nov 2026 15:09 |
| URI: | http://repository.essex.ac.uk/id/eprint/43495 |
Available files
Filename: 7000_Similarity_Dissimilarity_ (1).pdf
Licence: Creative Commons: Attribution 4.0