I am Zhenwei Zhang (张振威), a PhD student at Tsinghua University under the supervision of Professor Yuantao Gu. My research focuses on time series analysis, with a particular emphasis on time series forecasting and anomaly detection. Previously, I obtained my Bachelor’s degree from the Department of Electronic Engineering at Tsinghua University. During my undergraduate studies, I developed a strong foundation in signal processing and machine learning, which has been instrumental in my current research.

My PhD work aims to advance the state-of-the-art in time series analysis by developing novel deep learning models and algorithms. Some of my key research topics include:

• Multivariate Time Series Forecasting
• Time Series Forecasting for Peak-hour
• Anomaly Detection in Time Series

I am passionate about applying my research to real-world problems in domains like finance, healthcare, manufacturing, and more. I actively seek opportunities to collaborate with industry partners and translate my work into practical impact.

I am always eager to discuss research ideas and open to collaboration or visiting opportunities. If you are a researcher interested in time series analysis or machine learning more broadly, please feel free to reach out!

Publications

SageFormer: Series-Aware Framework for Long-Term Multivariate Time Series Forecasting [arxiv] [github]
Zhenwei Zhang, Linghang Meng, Yuantao Gu
IEEE Internet of Things Journal, 2024

Unravel Anomalies: An End-to-end Seasonal-Trend Decomposition Approach for Time Series Anomaly Detection [arxiv] [github]
Zhenwei Zhang, Ruiqi Wang, Ran Ding, Yuantao Gu
The 49th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024 (Oral, 6 out of 29 in ML4TS session)

Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting [arxiv] [github]
Zhenwei Zhang, Linghang Meng, Yuantao Gu
The 32nd ACM International Conference on Information and Knowledge Management (CIKM), 2023

ST2T: A Spatio-Temporal Transformer for Cellular Traffic Prediction in Digital Twin Systems
Zhenwei Zhang, Leon Yan, Yuantao Gu
IEEE 6th International Conference on Electronic Information and Communication Technology (ICEICT), 2023

Toward Digital Twin: Leveraging Pre-training Approaches for Multivariate Time Series Forecasting
Leon Yan, Zhenwei Zhang, Xin Wang, Yu Zhang, Yuantao Gu
IEEE 6th International Conference on Electronic Information and Communication Technology (ICEICT), 2023