Soft Contrastive Learning for Time Series

2023/12/27 by Seunghan Lee, Lee, Seunghan, Taeyoung Park +3 · 17 citations
Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2312.16424

openalex publication_date 2023/12/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way. However, contrasting similar time series instances or values from adjacent timestamps within a time series leads to ignore their inherent correlations, which results in deteriorating the quality of learned representations. To address this issue, we propose SoftCLT, a simple yet effective soft contrastive learning strategy for time series. This is achieved by introducing instance-wise and temporal contrastive loss with soft assignments ranging from zero to one. Specifically, we define soft assignments for 1) instance-wise contrastive loss by the distance between time series on the data space, and 2) temporal contrastive loss by the difference of timestamps. SoftCLT is a plug-and-play method for time series contrastive learning that improves the quality of learned representations without bells and whistles. In experiments, we demonstrate that SoftCLT consistently improves the performance in various downstream tasks including classification, semi-supervised learning, transfer learning, and anomaly detection, showing state-of-the-art performance. Code is available at this repository: https://github.com/seunghan96/softclt.

Cited by

• Contrastive Time Series Forecasting with Anomalies
• Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting
• A theoretical framework for self-supervised contrastive learning for continuous dependent data
• Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing
• FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model
• PLanTS: Periodicity-aware Latent-state Representation Learning for Multivariate Time Series
• Decomposing and Revising What Language Models Generate
• Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning
• A Unified Contrastive-Generative Framework for Time Series Classification
• Discrepancy-Aware Contrastive Adaptation in Medical Time Series Analysis
• CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation
• eMargin: Revisiting Contrastive Learning with Margin-Based Separation
• How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction
• Temporally-Aware Supervised Contrastive Learning for Polyp Counting in Colonoscopy
• Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis
• Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
• Universal Domain Adaptation Benchmark for Time Series Data Representation

Related

• Contrast All the Time: Learning Time Series Representation from Temporal Consistency
• Multi-Task Self-Supervised Time-Series Representation Learning
• TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning
• Time-Series Contrastive Learning against False Negatives and Class Imbalance
• StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal Contrast