Research
My research interest lies in optimization and machine learning in distributed or decentralized networks. Distributed or decentralized learning, which involves a series of single devices (workers) collaborating to train a machine learning model, usually serves as a promising solution in the following scenarios:
- Accelerate large-scale machine learning through parallel computation in data centers.
- Exploit the potential value of large-volume, heterogeneous, and privacy-sensitive data located at geographically distributed devices in settings like federated learning (FL) or multi-agent reinforcement learning (MARL).
As one of the central topics in distributed networks, my recent work focus on robust distributed optimization algorithms. Despite the well-known advantages, the distributed nature of networks makes them vulnerable to workers’ misbehaviors, especially in FL scenarios. This misbehavior, including malicious misleading, data poisoning, backdoor injection, and so on, can be abstracted into a so-called Byzantine attack model, where some workers (attackers) send arbitrary malicious messages to others. Hoping to fulfill the robustness requirement, I dedicate myself to designing and analyzing Byzantine-resilient optimization algorithms.
Journals
Byzantine-Resilient Decentralized Stochastic Optimization with Robust Aggregation Rules
Zhaoxian Wu, Tianyi Chen, Qing Ling
IEEE Transactions on Signal Processing (TSP), 2023
Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Data
Jie Peng, Zhaoxian Wu, Qing Ling
Information Sciences, 2022
Communication-censored Distributed Stochastic Gradient Descent
Weiyu Li, Zhaoxian Wu, Tianyi Chen, Liping Li, Qing Ling
IEEE Transactions on Neural Networks and Learning Systems(TNNLS), 2021
Byzantine-resilient Decentralized Policy Evaluation with Linear Function Approximation
Zhaoxian Wu, Han Shen, Tianyi Chen, Qing Ling
IEEE Transactions on Signal Processing (TSP), 2021
Federated Variance-reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks
Zhaoxian Wu, Qing Ling, Tianyi Chen, and Georgios B Giannakis
IEEE Transactions on Signal Processing (TSP), 2020
Conference
Distributed Online Learning With Adversarial Participants In An Adversarial Environment
Xingrong Dong, Zhaoxian Wu, Qing Ling, Zhi Tian
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
A Byzantine-resilient Dual Subgradient Method for Vertical Federated Learning
Kun Yuan, Zhaoxian Wu, Qing Ling
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022
Byzantine-resilient Decentralized TD Learning with Linear Function Approximation
Zhaoxian Wu, Han Shen, Tianyi Chen, Qing Ling
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
Byzantine-resilient Distributed Finite-sum Optimization over Networks
Zhaoxian Wu, Qing Ling, Tianyi Chen, and Georgios B Giannakis
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020
Preprints
|