MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

Zhe Li, Xuanxuan Li, Zhongwen Rao, Lujia Pan, Zenglin Xu

Abstract: Multivariate time series forecasting has been widely used in various practical scenarios. Recently, Transformer-based models have shown significant potential in forecasting tasks due to the capture of long-range dependencies. However, recent studies in the vision and NLP fields show that the role of attention modules is not clear, which can be replaced by other token aggregation operations. This paper investigates the contributions and deficiencies of attention mechanisms on the performance of time series forecasting. Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) modeling the mapping between the historical and predicting time series is crucial to the forecasting accuracy. To this end, we propose MTS-Mixers, which use two factorized modules to capture temporal and channel dependencies. Experimental results on several real-world datasets show that MTS-Mixers performs promising forecasting results with higher efficiency. Code is available at https://github.com/plumprc/MTS-Mixers.

External IDs:dblp:conf/ijcnn/LiLRPX25