Home
|
Chen Chen (谌晨)
I am a research scientist at Sony AI in the Privacy-Preserving Machine Learning team lead by Lingjuan Lyu.
Prior to that, I reveived my Ph.D. degree from Zhejiang University in 2022.
I am interested in trustworthy machine learning (privacy, security, etc). My current research focuses on federated learning and adversarial training.
[Google Scholar]
E-mail: chenchencc2021[at]gmail[dot]com
|
Education
Ph.D. in computer science and technology, Zhejiang University, China (Sep. 2017 - Dec. 2022)
Advisor: Professor Gang Chen
B.E. (honor) in computer science and technology, Chu Kochen Honors College (About 300 best students out of 6000 freshmen are chosen), Zhejiang University, China (Sep. 2013 - Jun. 2017)
Publications
(* indicates equal contributions)
Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning.
Yue Tan, Chen Chen, Weiming Zhuang, Xin Dong, Lingjuan Lyu, Guodong Long.
The Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS 2023).
Where Did I Come From? Origin Attribution of AI-Generated Images.
Zhenting Wang, Chen Chen, Yi Zeng, Lingjuan Lyu, Shiqing Ma.
The Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS 2023).
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation.
Jie Zhang, Chen Chen, Weiming Zhuang, Lingjuan Lyu.
International Conference on Computer Vision 2023 (ICCV 2023).
CalFAT: Calibrated Federated Adversarial Training with Label Skewness.
Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu.
The Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS 2022).
International Workshop on Trustable, Verifiable and Auditable Federated Learning in Conjunction with AAAI 2022 (FL-AAAI 2022) Best Student Paper.
Online Partial Label Learning.
Haobo Wang, Yuzhou Qiang, Chen Chen, Weiwei Liu, Tianlei Hu, Zhao Li, Gang Chen.
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML 2020).
Experience
Research intern in Sony AI, Japan (Sep. 2021 — Dec. 2022)
Focused on privacy and robustness in federated learning. Lead a project that focuses on robustness (against adversarial attack) in federated learning. Specifically, the project considered federated adversarial training under the challenging non-IID setting.
Visiting Ph.D. in National University of Singapore, Singapore (Nov. 2019 — Nov. 2020)
Focused on robust federated learning, which can defend against Byzantine attacks and improve performance in federated learning.
Professional Service
Reviewer: ICML, NeurIPS, ICLR, AAAI, IJCAI, etc.
|