I am now a researcher at Ubiquant AI lab. I got my PhD in Electrical Engineering from Tsinghua University in 2023. I obtained my B.E. degree from the same department in 2017. I visited the University of Southern California in 2019.
My research interests include AI for physics, graph neural networks, spatio-temporal data mining, and time series analysis.
Email: shz13@tsinghua.org.cn
Ph.D., Sept. 2017 - Jan. 2023
Electronic Engineering Department, Tsinghua University, Beijing, China
Visiting Scholar and Research Assistant, Apr. 2019 - Oct. 2019
Computer Science Department, University of Southern California, Los Angeles, CA, USA
B.E., Sept. 2013 - Jul. 2017
Electronic Engineering Department, Tsinghua University, Beijing, China
Learning to Simulate Crowd Trajectories with Graph Networks. [pdf]
Hongzhi Shi, Quanming Yao, Yong Li.
Proceedings of the ACM Web Conference (WebConf), 2023.
Predicting Origin-Destination Flow via Multi-Perspective Graph Convolutional Network. [pdf]
Hongzhi Shi, Quanming Yao, Qi Guo, Yaguang Li, Lingyu Zhang, Jieping Ye, Yong Li, Yan Liu.
IEEE International Conference on Data Engineering (ICDE), 2020.
(Research track, Short paper)
Semantics-Aware Hidden Markov Model for Human Mobility.[pdf]
Hongzhi Shi, Yong Li, Hancheng Cao, Xiangxin Zhou, Chao Zhang, Vassilis Kostakos.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021. (Impact factor = 3.857)
(Shorter version got accepted by SDM, Full paper, Acceptance rate≈22.7%)
DeepDPM: Dynamic Population Mapping via Deep Neural Network.[pdf]
Zefang Zong, Jie Feng, Kechun Liu, Hongzhi Shi, Yong Li.
AAAI Conference on Artificial Intelligence (AAAI), 2019.
(Full paper, Acceptance rate≈16.2%)
Discovering Periodic Patterns for Large Scale Mobile Traffic Data: Method and Applications.[pdf]
Hongzhi Shi, Yong Li.
IEEE transactions on mobile computing (TMC), 2018. (Impact factor = 4.098)
A Decomposition Approach for Urban Anomaly Detection Across Spatiotemporal Data.[pdf]
Mingyang Zhang, Tong Li, Hongzhi Shi, Yong Li, Pan Hui.
International Joint Conferences on Artificial Intelligence (IJCAI), 2019.
(Full paper, Acceptance rate≈17.9%)
Big data driven mobile traffic understanding and forecasting: A time series approach.[pdf]
Fengli Xu, Yujun Lin, Jiaxin Huang, Di Wu, Hongzhi Shi, Jeungeun Song, and Yong Li.
IEEE transactions on services computing (TSC), 2016. (Impact factor = 3.520)
Ubiquant AI Lab | AI Researcher | Beijing Jan. 2023 – Present
Developed deep models for returns and volatility forecasting in quantitative strategies for equities and futures
4Paradigm | Machine Learning Research Intern | Beijing Nov. 2019 – June 2022
Designed graph convolutional networks for pedestrian trajectory simulation and proposed to learn graph-like rules on knowledge graphs
DiDi AI Labs | Research Intern | Beijing Nov. 2018 – Mar. 2019
Designed multi-perspective graph convolutional networks for predicting origin-destination traffic
Tencent Institute | Research Intern | Beijing Dec. 2016 – May 2017
Used Spark to analyze trajectory data and implemented trajectory prediction algorithms to achieve higher performance
China Telecom Institute | Big Data Research Intern | Beijing Jul. 2016 – Sep. 2016
Processed the large-scale cellular traffic data in Shanghai and implemented an online population estimation algorithm
Data and Algorithm | Instructor: Prof. Jiansheng Chen Sep. 2018 - Jan. 2019
Senior Program Committee Member: IJCAI 2021
Program Committee Member: AAAI 2020-2023, ICML 2020 (top reviewer award)-2023, IJCAI 2020, ICLR 2021-2023, ICML 2021-2023, COMPASS 2021
Invited Journal Reviewer: ACM Transactions on Intelligent Systems and Technology
ICML 2020 Top Reviewer Award 2020
National Graduate Student Scholarship of China 2019
KDD 2019 Student Travel Award 2019
Mathematical Contest in Modeling: Honorable Mention 2016
Technological Innovation Excellence Scholarship 2015 & 2016
China Undergraduate Physics Competition: First Prize Nationwide 2014
Academic Excellence Scholarship 2014
Silver Medal, Chinese Physics Olympiad 2012
Programming Languages: Python, Java, C, C++, MATLAB
Big Data Platform Tools: Spark, Hadoop
Deep Learning Tools: Pytorch, Keras, TensorFlow
Other Tools: Git, Latex, Vim, Linux, MS Offices