· 2023· Review
Transformers in Time Series: A Survey
- 1,020citations
- 2023year
Short summary
This survey systematically reviews Transformer models adapted for time series analysis, highlighting their strengths in capturing long-range dependencies and their applications in forecasting, anomaly detection, and classification.
AI-generated from the title and abstract; the full text is not read.
Key points
- Transformers excel at capturing long-range dependencies, a key advantage for time series modeling.
- The survey categorizes time series Transformer adaptations by network structure modifications and by application tasks (forecasting, anomaly detection, classification).
- Empirical analyses cover performance, model size, and seasonal-trend decomposition of Transformers in time series.
- The paper provides a systematic review and discusses future research directions.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source., 2023 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science