Ziyu Zhou

Ziyu Zhou 周子渔

I am an MPhil student in the CityMind Lab at the Hong Kong University of Science and Technology (Guangzhou), under the supervision of Dr. Yuxuan Liang and Prof. James T. Kwok. Previously, I obtained B.Eng in Computer Science and Technology at the Beijing University of Technology, where I conducted research under the guidance of Prof. Gengyu Lyu at the DMS Lab in the College of Computer Science. During my undergraduate research, I was also privileged to receive guidance from Prof. Yin Liang and Prof. Xiliang Liu from the College of Computer Science. I had a wonderful internship experience at Beijing Founder Easiprint Co., Ltd. It is also my great pleasure to collaborate with members of the CityMind Lab as well as student researchers from outside the lab, including Yiming Huang, Yanyun Wang and Zihao Wang.

My current research interests focus on advancing data-driven deep learning, with a particular emphasis on spatiotemporal modeling and time series analysis for real-world applications.

Spatiotemporal Modeling and Time Series Analysis:
- Real-World Applications: Traffic management, meteorological forecasting, and neuroscience.
- Robust Deep Learning Approaches: Capturing complex spatial and temporal dependencies.
- Reliable Forecasting: Guiding decision-making and uncovering dynamic process evolution.
Multi-Modal Learning and Generative AI:
- Synergy with Time Series Analysis: Unlocking broader possibilities for real-world deployments.
- Versatile and Scalable Solutions: Pushing the boundaries of predictive modeling for tangible benefits in areas such as urban planning and neuroscience research.

Email1 / Email2 / Scholar / X / Github / CV

My Quote

"The purpose of computing is insight, not numbers." —— Richard Wesley Hamming

News

2025/5/26	Invited talk on "Deep Time Series Forecasting withTime-frequency Transformations" at BJUT.
2024/12/09	One paper about Point Cloud Salient Object Detection was accepted by AAAI'25.
2024/09/02	A new life at HKUST(GZ) has begun! Feel free to say hi if we cross paths on campus!
2024/06/29	I was awarded as Outstanding Graduate Thesis and Outstanding Graduates of Beijing.
2024/04/17	One paper about Time Series Forecasting was accepted by IJCAI'24.
2023/12/01	I decided to accept the MPhil offer from HKUST(GZ) Fok Ying Tung Graduate School.
2023/10/26	One paper about PM2.5 Forecasting was accepted by Atmosphere.
2023/08/25	One paper about ASD Detection was accepted by PRICAI'23.
2023/03/24	I achieved a satisfactory academic IELTS band score of 7.5 (8,8,6.5,6.5).

Research Programs & Publication

(* denotes corresponding author and ^ indicates equal contribution.)

	Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting Ziyu Zhou, Yiming Huang, Yanyun Wang, Yuankai Wu, James Kwok, Yuxuan Liang Arxiv(2025) 2508.01971 arXiv We fully leverage the Canonical Pre-Alignment technique for irregular multivariate time series forecasting, proposing a lightweight framework to process the pre-aligned series.
	Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting Ziyu Zhou, Jiaxi Hu, Qingsong Wen, James T. Kwok, Yuxuan Liang* Arxiv(2025) 2505.11781 arXiv We propose the Wavelet Derivative Transform to model the derivative of time series and integrate it into a multi-branch network (WaveTS) for efficient and effective time series long-term and short-term forecasting.
	SDformer: Transformer with Spectral Filter and Dynamic Attention for Multivariate Time Series Long-term Forecasting Ziyu Zhou, Gengyu Lyu, Yiming Huang, Zihao Wang, Ziyu Jia, Zhen Yang The 33rd International Joint Conference on Artificial Intelligence (IJCAI '24, CCF-A & CORE-A) The Only Long Oral Paper of the Time Series Session (1/12) Paper Link / PDF / Code / Poster We propose a novel Transformer architecture (named SDformer) for long-term time series forecasting. It is the first time to address the problem of smooth attention distribution when modeling time series data with a large number of variates.
	TimesNet-PM2.5: Interpretable TimesNet for Disentangling Intraperiod and Interperiod Variations in PM2.5 Prediction Yiming Huang^, Ziyu Zhou^, Zihao Wang^, Xiaoying Zhi, Xiliang Liu* Atmosphere (JCR-Q3) Paper Link In this paper, we accomplish task-specific adaption of TimesNet (ICLR '23) named TimesNet-PM2.5. This specialized version improved the performance and interpretability of the PM2.5 prediction of Haikou, Hainan Province.
	STFM: Enhancing Autism Spectrum Disorder Classification Through Ensemble Learning-Based Fusion of Temporal and Spatial fMRI Patterns Ziyu Zhou^, Yiming Huang^, Yining Wang^, Yin Liang* The 20th Pacific Rim International Conference on Artificial Intelligence (PRICAI '23, CCF-C & CORE-B) Paper Link / PDF We propose a Spatial and Temporal framework named STFM based on cross-attention for better autism spectrum disorder classification. The results show that STFM's classification accuracy surpassed that of many machine learning models.
	CoC-GAN: Employing Context Cluster for Unveiling a New Pathway in Image Generation Zihao Wang^, Yiming Huang^, Ziyu Zhou^ Arxiv(2023) 2308.11857 arXiv We employ Context-Clustering Block (ICLR '23) into GAN for better interpretability.