TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Wang, Yuxuan, Wu, Haixu, Dong, Jiaxiang, Liu, Yong, Qiu, Yunzhong, Zhang, Haoran, Wang, Jianmin, Long, Mingsheng
–arXiv.org Artificial Intelligence
Recent studies have demonstrated remarkable performance in time series forecasting. However, due to the partially-observed nature of real-world applications, solely focusing on the target of interest, so-called endogenous variables, is usually insufficient to guarantee accurate forecasting. Notably, a system is often recorded into multiple variables, where the exogenous series can provide valuable external information for endogenous variables. Thus, unlike prior well-established multivariate or univariate forecasting that either treats all the variables equally or overlooks exogenous information, this paper focuses on a practical setting, which is time series forecasting with exogenous variables. We propose a novel framework, TimeXer, to utilize external information to enhance the forecasting of endogenous variables. With a deftly designed embedding layer, TimeXer empowers the canonical Transformer architecture with the ability to reconcile endogenous and exogenous information, where patch-wise self-attention and variate-wise cross-attention are employed. Moreover, a global endogenous variate token is adopted to effectively bridge the exogenous series into endogenous temporal patches. Experimentally, TimeXer significantly improves time series forecasting with exogenous variables and achieves consistent state-of-the-art performance in twelve real-world forecasting benchmarks.
arXiv.org Artificial Intelligence
Feb-29-2024
- Country:
- Pacific Ocean > North Pacific Ocean
- San Francisco Bay (0.04)
- North America
- United States
- Pennsylvania (0.04)
- New Jersey (0.04)
- Maryland (0.04)
- California > San Francisco County
- San Francisco (0.04)
- Trinidad and Tobago > Trinidad
- United States
- Europe
- Asia > Middle East
- Jordan (0.04)
- Pacific Ocean > North Pacific Ocean
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Energy > Power Industry (0.95)
- Technology: