paper-with-me

Papers

Self-Supervised Learning for Time Series: Contrastive or Generative?

2024-03-14 · Ziyu Liu, Azadeh Alavi, Minyi Li, Xiang Zhang

Self-supervised learning (SSL) has recently emerged as a powerful approach to learning representations from large-scale unlabeled data, showing promising results in time series analysis. The self-supervised representation learning can be categorized into two mainstream: contrastive and generative. In this paper, we will present a comprehensive comparative study between contrastive and generative methods in time series. We first introduce the basic frameworks for contrastive and generative SSL, respectively, and discuss how to obtain the supervision signal that guides the model optimization. We then implement classical algorithms (SimCLR vs. MAE) for each type and conduct a comparative analysis in fair settings. Our results provide insights into the strengths and weaknesses of each approach and offer practical recommendations for choosing suitable SSL methods. We also discuss the implications of our findings for the broader field of representation learning and propose future research directions. All the code and data are released at \url{https://github.com/DL4mHealth/SSL_Comparison}.

📄 PDF Abstract BibTeX arXiv:2403.09809

Code (1)

dl4mhealth/ssl_comparison 공식 구현 pytorch

Tasks

Model OptimizationRepresentation LearningSelf-Supervised LearningTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

A Unified Contrastive-Generative Framework for Time Series Classification

2025-08-13 · Ziyu Liu, Azadeh Alavi, Minyi Li, Xiang Zhang arxiv

Self-supervised learning (SSL) for multivariate time series mainly includes two paradigms: contrastive methods that excel at instance discrimination and generative approaches that model data distributions. While effectiv…

Time Series ClassificationSelf-Supervised LearningContrastive Learning

Ti-MAE: Self-Supervised Masked Time Series Autoencoders

2023-01-21 · Zhe Li, Zhongwen Rao, Lujia Pan, Pengyun Wang 외

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-t…

Contrastive LearningMultivariate Time Series ForecastingRepresentation LearningTime Series+2

Unsupervised Driving Event Discovery Based on Vehicle CAN-data

2023-01-12 · Thomas Kreutz, Ousama Esbel, Max Mühlhäuser, Alejandro Sanchez Guinea

The data collected from a vehicle's Controller Area Network (CAN) can quickly exceed human analysis or annotation capabilities when considering fleets of vehicles, which stresses the importance of unsupervised machine le…

Contrastive LearningSelf-Supervised LearningTime SeriesTime Series Analysis

CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection

2023-08-18 · Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan, Charu C. Aggarwal 외

One main challenge in time series anomaly detection (TSAD) is the lack of labelled data in many real-life scenarios. Most of the existing anomaly detection methods focus on learning the normal behaviour of unlabelled tim…

Anomaly DetectionContrastive LearningRepresentation LearningTime Series+1

Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects

2023-06-16 · Kexin Zhang, Qingsong Wen, Chaoli Zhang, Rongyao Cai 외

Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training a…

Anomaly DetectionSelf-Supervised LearningTime SeriesTime Series Analysis+1