eMargin: Revisiting Contrastive Learning with Margin-Based Separation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918098781601792 |
|---|---|
| author | Shamba, Abdul-Kazeem Bach, Kerstin Taylor, Gavin |
| author_facet | Shamba, Abdul-Kazeem Bach, Kerstin Taylor, Gavin |
| contents | We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether an adaptive margin (eMargin), adjusted based on a predefined similarity threshold, can improve the separation between adjacent but dissimilar time steps and subsequently lead to better performance in downstream tasks. Our study evaluates the impact of this modification on clustering performance and classification in three benchmark datasets. Our findings, however, indicate that achieving high scores on unsupervised clustering metrics does not necessarily imply that the learned embeddings are meaningful or effective in downstream tasks. To be specific, eMargin added to InfoNCE consistently outperforms state-of-the-art baselines in unsupervised clustering metrics, but struggles to achieve competitive results in downstream classification with linear probing. The source code is publicly available at https://github.com/sfi-norwai/eMargin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | eMargin: Revisiting Contrastive Learning with Margin-Based Separation Shamba, Abdul-Kazeem Bach, Kerstin Taylor, Gavin Machine Learning Artificial Intelligence We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether an adaptive margin (eMargin), adjusted based on a predefined similarity threshold, can improve the separation between adjacent but dissimilar time steps and subsequently lead to better performance in downstream tasks. Our study evaluates the impact of this modification on clustering performance and classification in three benchmark datasets. Our findings, however, indicate that achieving high scores on unsupervised clustering metrics does not necessarily imply that the learned embeddings are meaningful or effective in downstream tasks. To be specific, eMargin added to InfoNCE consistently outperforms state-of-the-art baselines in unsupervised clustering metrics, but struggles to achieve competitive results in downstream classification with linear probing. The source code is publicly available at https://github.com/sfi-norwai/eMargin. |
| title | eMargin: Revisiting Contrastive Learning with Margin-Based Separation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.14828 |