张晓今
Xiaojin Zhang
Postdoctoral Fellow
Computer Science and Engineering
The Hong Kong University of Science and Technology
xiaojinzhang@ust.hk
Bio
I am a Postdoctoral Fellow at CSE, HKUST. I am very fortunate to be advised by Prof. Qiang Yang and Prof. Kai Chen. In 2021, I completed my PhD at CSE, CUHK. My advisors were Prof. Shengyu Zhang and Prof. Siu On Chan. Before that, I obtained my M.S. in Computer Application Technology from the Institute of Computing Technology, the Chinese Academy of Sciences, with the supervision of Prof. Si-Min He. I obtained my B.S. in Statistics and Economics (Elite Class) from the School of Mathematics and Statistics, Shandong University, Weihai.
I like designing efficient algorithms. I have broad interests in classical theoretical computer science and modern machine learning.
Please feel free to email me if you are interested in working with me on fedearted learning and transfer learning. Working on one project at a time with the same partner is my preferred way of collaboration.
Preprints
Federated PAC Learning
Xiaojin Zhang, Anbu Huang, Lixin Fan, Kai Chen, Qiang Yang.
Towards Achieving Lossless Utility for Privacy-Preserving Federated Learning
Xiaojin Zhang, Lixin Fan, Kai Chen, Qiang Yang.
Theoretically Principled Federated Learning for Balancing Privacy and Utility
Xiaojin Zhang, Wenjie Li, Shaofeng Jiang, Yan Kang, Kai Chen, Qiang Yang.
MetaNFL: Practical Trade-off Between Privacy, Utility and Efficiency in Federated Learning
Xiaojin Zhang, Shaofeng Jiang, Yan Kang, Lixin Fan, Kai Chen, Qiang Yang.
A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning
Yan Kang, Jiahuan Luo, Yuanqin He, Xiaojin Zhang, Lixin Fan, Qiang Yang.
A Game-theoretic Utility Model for Federated Learning
Xiaojin Zhang, Lixin Fan, Siwei Wang, Kai Chen, Qiang Yang.
Near-optimal Algorithm for Distribution-free Junta Testing
Xiaojin Zhang.
Blurb on Property Testing Review.Improved Algorithm for Permutation Testing
Xiaojin Zhang.
Contextual Combinatorial Conservative Bandits
Xiaojin Zhang, Shuai Li, Weiwen Liu, Shengyu Zhang.
Publications
* indicates alphabetic ordering, # indicates equal contributions.
Trading Off Privacy, Utility and Efficiency in Federated Learning
Xiaojin Zhang, Yan Kang, Kai Chen, Lixin Fan, Qiang Yang.
Transactions on Intelligent Systems and Technology [TIST] .No Free Lunch Theorem for Security and Utility in Federated Learning
Xiaojin Zhang#, Hanlin Gu#, Lixin Fan, Kai Chen, Qiang Yang.
Transactions on Intelligent Systems and Technology [TIST] . PDFVariance-Dependent Best Arm Identification
Pinyan Lu*, Chao Tao*, Xiaojin Zhang*. [alphabetic ordering]
In Proceedings of the Conference on Uncertainty in Artificial Intelligence [UAI 2021]. PDFAchieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
Chung-Wei Lee*, Haipeng Luo*, Chen-Yu Wei*, Mengxiao Zhang*, Xiaojin Zhang*. [alphabetic ordering]
In Proceedings of the 36th International Conference on Machine Learning [ICML 2021]. PDFAdaptive Double-Exploration Tradeoff for Outlier Detection
Xiaojin Zhang, Honglei Zhuang, Shengyu Zhang, Yuan Zhou.
The Thirty-Fourth AAAI Conference on Artificial Intelligence [AAAI 2020]. PDFpGlyco 2.0 enables precision N-glycoproteomics with comprehensive quality control and one-step mass spectrometry for intact glycopeptide identification
Ming-Qi Liu#, Wen-Feng Zeng#, Pan Fang#, Wei-Qian Cao#, Chao Liu#, Guo-Quan Yan, Yang Zhang, Chao Peng, Jian-Qiang Wu, Xiao-Jin Zhang, Hui-Jun Tu, Hao Chi, Rui-Xiang Sun, Yong Cao, Meng-Qiu Dong, Bi-Yun Jiang, Jiang-Ming Huang, Hua-Li Shen, Catherine C. L. Wong, Si-Min He, Peng-Yuan Yang.
Nature Communications, 8, 438, 2017. PDFTrends in Mass Spectrometry-Based Large-Scale N-Glycopeptides Analysis
Wen-Feng Zeng, Yang Zhang, Ming-Qi Liu, Jian-Qiang Wu, Xiao-Jin Zhang, Hao Yang, Chao Liu, Hao Chi, Kun Zhang, Rui-Xiang Sun, Peng-Yuan Yang, Si-Min He.
Progress in Biochemistry and Biophysics, 2016, 43(6):550-562. PDFSelected Awards
2017-2021 Postgraduate Studentship, CUHK
06/2017 Excellent Master's Thesis
04/2013 The Mathematical Contest in Modeling (MCM), Honorable Mentions
10/2012 China Undergraduate Mathematical Contest of Modeling (CUMCM), National First Prize
11/2011 National Scholarship
05/2011 Aerobic Gymnastics, Second Prize in College
Patents
A comprehensive system for constructing N-glycan databases based on linear canonical representations
Xiao-Jin Zhang, Wen-Feng Zeng, Jian-Qiang Wu, Rui-Xiang Sun, Si-Min He.
PDFA comprehensive system for intact glycopeptide identification
Wen-Feng Zeng, Ming-Qi Liu, Xiao-Jin Zhang, Jian-Qiang Wu, Yang Zhang, Rui-Xiang Sun, Peng-Yuan Yang, Si-Min He.
PDF