Transformers in Time Series: A Survey

TL;DR

This survey comprehensively reviews recent advances in Transformer models for time series analysis, highlighting their structural adaptations, applications, and performance insights, and discusses future research directions.

Contribution

First systematic review of Transformer applications in time series, summarizing structural modifications, categorizing tasks, and providing empirical performance analysis.

Findings

Transformers excel in capturing long-range dependencies in time series.

Structural adaptations improve Transformer effectiveness for specific time series tasks.

Empirical analysis reveals performance variations based on model size and seasonal components.

Abstract

Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also triggered great interest in the time series community. Among multiple advantages of Transformers, the ability to capture long-range dependencies and interactions is especially attractive for time series modeling, leading to exciting progress in various time series applications. In this paper, we systematically review Transformer schemes for time series modeling by highlighting their strengths as well as limitations. In particular, we examine the development of time series Transformers in two perspectives. From the perspective of network structure, we summarize the adaptations and modifications that have been made to Transformers in order to accommodate the challenges in time series analysis. From the perspective of applications, we categorize time series Transformers based on common tasks including forecasting, anomaly detection, and classification. Empirically, we perform robust analysis, model size analysis, and seasonal-trend decomposition analysis to study how Transformers perform in time series. Finally, we discuss and suggest future directions to provide useful research guidance. To the best of our knowledge, this paper is the first work to comprehensively and systematically summarize the recent advances of Transformers for modeling time series data. We hope this survey will ignite further research interests in time series Transformers.