Date & Time: 

   2024 /11 / 01  (Fri) 14:20 - 16:20

 

Location: 

   Delta Building R216, NTHU

 

Speaker: 

    劉俊宏 教授 Prof. Chun-Hung Liu

   Dept. of Electrical and Computer Engineering, Mississippi State University

 

Topic: 

  Collective Federated Learning

 

Abstract: 

   The thriving of machine learning (ML) technologies drives the evolution of solving many diverse scientific and engineering problems, from model-based approaches to data-driven ones. How to effectively exploit a considerable amount of data distributed over a large territory safely and efficiently is the key to making ML have much more transformative impacts on data-driven solutions to complex real-world problems. Traditional centralized ML cannot efficiently exploit “networked intelligence” by learning from big data distributed over a huge network. Federated Learning (FL) recently proposed can make the server conduct a learning task without raw data delivered from its clients. It accordingly is a viable approach to collective intelligence. Nonetheless, the performances of traditional FL frameworks are sensitive to heterogeneous network conditions, such as data and client heterogeneity, network resources, networking conditions, etc. This talk will introduce a Collective FL (CFL) approach to unlock networked intelligence with practical networking and communication limitations and achieve high reliability, scalability, and adaptability learning performances. As such, it is expected to significantly improve the performances of FL over networks with system impairment and data heterogeneity.

 

Autobiography: 

  Dr. Liu is an Associate Professor in the Department of Electrical and Computer Engineering at Mississippi State University (MSU). Before joining MSU, he was with University of Michigan and National (Yang Ming) Chiao Tung University, Hsinchu, Taiwan, and Qualcomm Inc. He received a B.S. degree from National Taiwan University, an M.S. degree from Massachusetts Institute of Technology, and a Ph.D. degree in Electrical and Computer Engineering from the University of Texas at Austin. He received several prestigious awards in research and education, such as Faculty Fellowship Award from Air Force Research Lab. (AFRL) in 2023, Yang Faculty Research Award from MSU in 2022, Young Scholar Research Award from the Ministry of Science and Technology of Taiwan in 2015, Best Paper Awards from IEEE Globecom Conference in 2014 and 2008, etc.