arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.01034cs.LGcs.AI
收藏

多任务自监督时间序列表示学习

Multi-Task Self-Supervised Time-Series Representation Learning

Korea University(高丽大学)

Heejeong Choi, Pilsung Kang

摘要:

时间序列表示学习可以从具有时间动态和稀疏标签的数据中提取表示。当标记数据稀疏但未标记数据丰富时,对比学习,即,一种用于学习潜在空间的框架已经显示出出色的性能,在该潜在空间中,相似的样本彼此接近,而不相似的样本彼此远离。这种策略可以鼓励不同的时间序列表示的一致性,这取决于积极的对选择和对比损失。我们提出了一种新的时间序列表示学习方法,结合了自监督任务的上下文,时间和转换一致性的优势。它允许网络学习各种下游任务和域的一般表示。具体来说,我们首先采用数据预处理,为每个自监督任务生成积极和消极对。然后,该模型执行上下文,时间和变换对比学习,并使用它们的对比损失联合优化。我们进一步研究了一种不确定性加权方法,通过考虑每个一致性的贡献来实现有效的多任务学习。我们评估了三个下游任务的建议框架:时间序列分类,预测和异常检测。实验结果表明,该方法不仅在这些下游任务上优于基准模型,而且在跨域迁移学习中也显示出有效性。

英文摘要:

Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent space where similar samples are close to each other while dissimilar ones are far from each other, has shown outstanding performance. This strategy can encourage varied consistency of time-series representations depending on the positive pair selection and contrastive loss. We propose a new time-series representation learning method by combining the advantages of self-supervised tasks related to contextual, temporal, and transformation consistency. It allows the network to learn general representations for various downstream tasks and domains. Specifically, we first adopt data preprocessing to generate positive and negative pairs for each self-supervised task. The model then performs contextual, temporal, and transformation contrastive learning and is optimized jointly using their contrastive losses. We further investigate an uncertainty weighting approach to enable effective multi-task learning by considering the contribution of each consistency. We evaluate the proposed framework on three downstream tasks: time-series classification, forecasting, and anomaly detection. Experimental results show that our method not only outperforms the benchmark models on these downstream tasks, but also shows efficiency in cross-domain transfer learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑