Ziang Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ziang Chen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Shiwei Guo
Chinese Academy of Sciences
2 shared publications - Yi Wang
Chinese Academy of Sciences
2 shared publications - Yupeng Ma
Chinese Academy of Sciences
2 shared publications Yunfei Han
Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Urumqi China
1 shared publication- Yunfei Han
Chinese Academy of Sciences
1 shared publication
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 517-526
SCFormer: Structured Channel-Wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting
- 2 January 2026
- Published by Springer Nature
- p. 517-526
SCFormer: Structured Channel-Wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting
- Open Access
SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting
The Transformer model has shown strong performance in multivariate time series forecasting by leveraging channel-wise self-attention. However, this approach lacks temporal constraints when computing temporal features and does not utilize cumulative historical series effectively.To address these limitations, we propose the Structured Channel-wise Transformer with Cumulative Historical state (SCFormer). SCFormer introduces temporal constraints to all linear transformations, including the query, key, and value matrices, as well as the fully connected layers within the Transformer. Additionally, SCFormer employs High-order Polynomial Projection Operators (HiPPO) to deal with cumulative historical time series, allowing the model to incorporate information beyond the look-back window during prediction. Extensive experiments on multiple real-world datasets demonstrate that SCFormer significantly outperforms mainstream baselines, highlighting its effectiveness in enhancing time series forecasting. The code is publicly available at https://github.com/ShiweiGuo1995/SCFormer
Open AccessSCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting
The Transformer model has shown strong performance in multivariate time series forecasting by leveraging channel-wise self-attention. However, this approach lacks temporal constraints when computing temporal features and does not utilize cumulative historical series effectively.To address these limitations, we propose the Structured Channel-wise Transformer with Cumulative Historical state (SCFormer). SCFormer introduces temporal constraints to all linear transformations, including the query, key, and value matrices, as well as the fully connected layers within the Transformer. Additionally, SCFormer employs High-order Polynomial Projection Operators (HiPPO) to deal with cumulative historical time series, allowing the model to incorporate information beyond the look-back window during prediction. Extensive experiments on multiple real-world datasets demonstrate that SCFormer significantly outperforms mainstream baselines, highlighting its effectiveness in enhancing time series forecasting. The code is publicly available at https://github.com/ShiweiGuo1995/SCFormer