Scalable Transformer for High Dimensional Multivariate Time Series Forecasting Zhou, Xin Wang, Weiqing Buntine, Wray Qu, Shilin Sriramulu, Abishek Tan, Weicong Bergmeir, Christoph Norbert Multivariate Time Series Forecasting High-dimensional Time Series Forecast accuracy Deep models for Multivariate Time Series (MTS) forecasting have recently demonstrated significant success. Channel-dependent models capture complex dependencies that channel-independent models cannot capture. However, the number of channels in real-world applications outpaces the capabilities of existing channel-dependent models, and contrary to common expectations, some models underperform the channel-independent models in handling high-dimensional data, which raises questions about the performance of channel-dependent models. To address this, our study first investigates the reasons behind the suboptimal performance of these channel-dependent models on high-dimensional MTS data. Our analysis reveals that two primary issues lie in the introduced noise from unrelated series that increases the difficulty of capturing the crucial inter-channel dependencies, and challenges in training strategies due to high-dimensional data. To address these issues, we propose STHD, the Scalable Transformer for High-Dimensional Multivariate Time Series Forecasting. STHD has three components: a) Relation Matrix Sparsity that limits the noise introduced and alleviates the memory issue; b) ReIndex applied as a training strategy to enable a more flexible batch size setting and increase the diversity of training data; and c) Transformer that handles 2-D inputs and captures channel dependencies. These components jointly enable STHD to manage the high-dimensional MTS while maintaining computational feasibility. Furthermore, experimental results show STHD's considerable improvement on three high-dimensional datasets: Crime-Chicago, Wiki-People, and Traffic. The source code and dataset are publicly available https://github.com/xinzzzhou/ScalableTransformer4HighDimensionMTSF.git. 2025-04-01T07:50:18Z 2025-04-01T07:50:18Z 2024-08-21 journal article Xin Zhou et al. Scalable Transformer for High Dimensional Multivariate Time Series Forecasting CIKM ’24, October 21–25, 2024, Boise, ID, USA. https://doi.org/10.1145/3627673.3679757 https://hdl.handle.net/10481/103364 10.1145/3627673.3679757 eng http://creativecommons.org/licenses/by/4.0/ open access Atribución 4.0 Internacional Association for Computing Machinery