Tao Xing

Tao Xing

Auto-generated profile, based on publicly available information

Tao Xing

School of Mechanical and Automotive Engineering, Shanghai University of Engineering and Technology, Shanghai, China

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

1 July 2023
Verified
Conference Paper
Closed access
BZBo Zhang
Bo Zhang
SHShuo Huang
Shuo Huang
HCHelei Cui
Helei Cui
XLXiaoning Liu
Xiaoning Liu
ZYZhiwen Yu
Zhiwen Yu
TXTao Xing
Tao Xing
The rapid evolution of public knowledge is the trend of the present era; rendering previously collected data susceptible to obsolescence. The continuously generated new knowledge could further affect the performance of the model trained with previous data, such a phenomenon is called temporal misalignment. A vanilla mitigation approach is to periodically update the model in a centralized learning scheme. However, in a decentralized learning framework like Federated Learning (FL), such a patch requires clients to upload the data, which contradicts FL's intention to protect clients' privacy. Furthermore, considering the stationary defenses in FL, new knowledge could be misjudged and rejected as malicious attacks, which hinders the further update of the model. Yet dynamically adapting defenses requires meticulous fine-tuning and harms the scalability. Thus in this poster, we raise such practical concern and discuss it in the context of FL. We then build a prototype of a GPT2-based FL framework and conduct experiments to demonstrate our perspective. The performance in new knowledge drops by 33.47% compared with the previous data, which justify the FL with defenses strategy can misjudge the new knowledge.

22 March 2004
Verified
Conference Paper
Closed access
YLYaqiang Liu
Yaqiang Liu
HLHongdi Li
Hongdi Li
YWYu Wang
Yu Wang
TXTao Xing
Tao Xing
HBH. Baghaei
H. Baghaei
WWWai-Hoi Wong
Wai-Hoi Wong