I am a third-year Ph.D. student in Computer Science at Georgia Institute of Technology, advised by Prof. Steve Mussmann. I received my bachelor’s degree from Turing Class at Zhejiang University, an honors program jointly cultivated by Chu Kochen Honors College and College of Computer Science and Technology. I am interested in how machine learning models can effectively and efficiently learn from limited labeled data in an explainable way. During my first year, I worked on temporal evolution with large language models that can adaptively learn from both labeled and unlabeled new knowledge over time while preserving useful information in old knowledge. Before that, I worked on several research projects related to federated learning, including its heterogeneity, reliability, security, accessibility, effectiveness, and privacy. I also participated in various projects related to visual analytics, including machine learning diagnosis and sports data analysis.
Myopic Bayesian Decision Theory for Batch Active Learning with Partial Batch Label Sampling
Kangping Hu, Stephen Mussmann
[PDF] [Code]
UniFed: All-In-One Federated Learning Platform to Unify Open-Source Frameworks
Xiaoyuan Liu, Tianneng Shi, Chulin Xie, Qinbin Li, Kangping Hu, Haoyu Kim, Xiaojun Xu, The-Anh Vu-Le, Zhen Huang, Arash Nourian, Bo Li, Dawn Song
[PDF] [Code] [Website]
Powered by Jekyll and Minimal Light theme.