I am a Ph.D. student at University of California, Santa Cruz, CA, USA. I am working under the guidance of Prof. Yang Liu. My current research interests include weakly-supervised learning and federated learning. I also did some research on topics such as distributed optimization for mobile networks, fog computing, and signal processing on graph.
Prior to UCSC, I received the B.S. degree from the University of Electronic Science and Technology of China (UESTC), Chengdu, China, in 2016, under the supervision of Prof. Wenhui Xiong, and received the M.S. degree from ShanghaiTech University, Shanghai, China, under the supervision of Prof. Xiliang Luo.Google Site        Resume
[2021.03] [CVPR 2021 (*oral)] One paper is accepted as an oral presentation at CVPR 2021! This paper studies how peer loss performs when facing human-level instance-dependent label noise. We use some second-order information to cancel the effect of instance-dependent label noise: [paper].
[2021.01] [ICLR 2021] We provide a dynamic sample sieve approach to deal with instance-dependent label noise. We have both theoretical guarantees (learn the clean distributions and sieve our corrupted examples) and experimental implementations (separate clean/corrupted examples, then apply semi-supervised learning techniques) [paper] [code]
[2020.12] [SIGMETRICS 2021] Our work Federated Bandit: A Gossiping Approach is accepted to ACM SIGMETRICS 2021！ In our paper, we build an analytical framework to study a private and decentralized bandit setting ("Federated Bandit"). We provide the concentration bound when heterogeneous rewards can only be shared via gossiping over a network. [paper]