InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting

arXiv:2403.02814v1 Announce Type: new
Abstract: Transformer has become one of the most popular architectures for multivariate time series (MTS) forecasting. Recent Transformer-based MTS models generally prefer channel-independent structures with the observation that channel independence can alleviate noise and distribution drift issues, leading to more robustness. Nevertheless, it is essential to note that channel dependency remains an inherent characteristic of MTS, carrying valuable information. Designing a model that incorporates merits of both channel-independent and channel-mixing structures is a key to further …

abstract architectures arxiv become channels cs.ai cs.lg distribution drift forecasting global independent information multivariate noise observation popular series time series time series forecasting transformer type