为时间序列对比学习引入自适应边界，提升聚类效果但下游分类表现不佳。
eMargin: Revisiting Contrastive Learning with Margin-Based Separation
- 在对比损失中加入基于相似度阈值的自适应边界（eMargin）
- 聚类指标优于现有方法，但线性探测分类性能未达领先水平
- 揭示了无监督聚类高分不等于下游任务有效性的风险
我们重新审视了时间序列表示学习中的对比学习框架，探究在对比损失函数中引入自适应边界（eMargin）的效果。该边界根据预设的相似度阈值动态调整，旨在增强相邻但不相似时间步之间的分离。我们在三个基准数据集上评估了该改进对聚类性能和分类任务的影响。结果表明，尽管eMargin在无监督聚类指标上持续优于当前最优基线，但在下游分类任务中使用线性探测时仍难以取得有竞争力的结果。这一发现提示：高聚类得分并不意味着学到的嵌入在实际任务中具有意义或有效性。代码已公开于 https://github.com/sfi-norwai/eMargin。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。