Ziyu Zhou 周子渔

I am an MPhil student in the CityMind Lab at HKUST(GZ), under the supervision of Prof. Yuxuan Liang. 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. I had a wonderful internship experience at Beijing Founder Electronics Co., Ltd.

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.

  1. 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.
  2. 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.

Through this integrative perspective, I aim to create data-driven, general-purpose solutions that deepen our understanding of dynamic processes and deliver significant value in high-stakes environments.

Email1  /  Email2  /  Scholar  /  X  /  Github  /  CV

profile photo

My Quote

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

News
News
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.)
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.

Education Background

Hong Kong University of Science and Technology(GZ)

MPhil in Data Science and Analytics

2024.09 - 2026.06(expected), Guangzhou, Nansha

Bejing University of Technology

BEng in Computer Science and Technology with Honours Degrees

Outstanding Graduate Thesis 北京市优秀毕业设计（论文）(Top 0.7%)

Outstanding Graduates 北京市优秀毕业生(Top 11%)

2020.09 - 2024.07, Beijing, Chaoyang