Pengxin Guo (郭鹏鑫)
PhD Candidate
guopx (at) connect.hku.hk
School of Computing and Data Science
The University of Hong Kong
Hong Kong, China
Biography
I'm currently a third-year PhD candidate in The University of Hong Kong, supervised by Prof. Liangqiong Qu.
I received my Master's degree in Southern University of Science and Technology under the supervision of Prof. Yu Zhang in 2023, and a B.Eng. degree in Northeast Forestry University in 2020.
I am interested in the foundations of machine learning including multi-task learning, transfer learning, and federated learning and their industrial applications.
Google Scholar |
Semantic Scholar |
DBLP |
OpenReview |
LinkedIn
News
Publications
2025
- Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting
Pengxin Guo, Pengrong Jin, Ziyue Li, Lei Bai, and Yu Zhang.
IEEE Transactions on Intelligent Transportation Systems (TITS), 2025. - Selective Aggregation for Low-Rank Adaptation in Federated Learning
Pengxin Guo, Shuang Zeng, Yanran Wang, Huijie Fan, Feifei Wang, and Liangqiong Qu.
International Conference on Learning Representations (ICLR), 2025. - A New Federated Learning Framework Against Gradient Inversion Attacks
Pengxin Guo*, Shuang Zeng*, Wenhao Chen, Xiaodan Zhang, Weihong Ren, Yuyin Zhou, and Liangqiong Qu.
AAAI Conference on Artificial Intelligence (AAAI), 2025.
2024
- A Versatile Framework for Unsupervised Domain Adaptation Based on Instance Weighting
Jinjing Zhu, Feiyang Ye, Qiao Xiao, Pengxin Guo, Yu Zhang, and Qiang Yang.
IEEE Transactions on Image Processing (TIP), 2024. - Tackling Data Heterogeneity in Federated Learning via Loss Decomposition
Shuang Zeng*, Pengxin Guo*, Shuai Wang, Jianbo Wang, Yuyin Zhou, and Liangqiong Qu.
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024.
Before 2024
- Unsupervised Domain Adaptation via Bidirectional Cross-Attention Transformer
Xiyu Wang, Pengxin Guo, and Yu Zhang.
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2023. - Selective Partial Domain Adaptation
Pengxin Guo, Jinjing Zhu, and Yu Zhang.
British Machine Vision Conference (BMVC), 2022. - Learning Feature Alignment Architecture for Domain Adaptation
Zhixiong Yue, Pengxin Guo, Yu Zhang, and Christy Liang.
International Joint Conference on Neural Networks (IJCNN), 2022. - Multi-Objective Meta Learning
Feiyang Ye*, Baijiong Lin*, Zhixiong Yue, Pengxin Guo, Qiao Xiao, and Yu Zhang.
Conference on Neural Information Processing Systems (NeurIPS), 2021. - Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network
Pengxin Guo, Chang Deng, Linjie Xu, Xiaonan Huang, and Yu Zhang.
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2021.
Preprints
- Exploring Federated Pruning for Large Language Models
Pengxin Guo, Yinong Wang, Wei Li, Mengting Liu, Ming Li, Jinkai Zheng, and Liangqiong Qu
arXiv:2505.13547, 2025. - Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks
Pengxin Guo*, Runxi Wang*, Shuang Zeng, Jinjing Zhu, Haoning Jiang, Yanran Wang, Yuyin Zhou, Feifei Wang, Hui Xiong, and Liangqiong Qu
arXiv:2503.11514, 2025.