Date & Time: 

   2025 /09 / 12  (Fri) 14:20 - 16:20

 

Location: 

   Delta Building R216, NTHU

 

Speaker: 

   張佑榕 博士

   中央研究院 資訊科技創新研究中心

 

Topic: 

  Reconfigurable Intelligent Surface (RIS)-Aided Communication: A Graph Neural Network Approach

 

Abstract: 

  In this talk, we introduce reconfigurable intelligent surface (RIS)-aided multiuser communication systems. We focus on scenarios where a base station (BS) transmits data to multiple users with the help of one or more RISs and/or a relay. We study the joint beamforming design for the BS, relay, and RIS. Traditional optimization-based approaches often suffer from high computational cost and yield suboptimal performance. We propose a graph neural network (GNN) approach that learns joint beamforming strategies in an unsupervised fashion by exchanging and updating relevant relational information embedded in the graph representation of the transmission system. The proposed GNN offers superior performance, robustness, generalizability, and reduced complexity compared to existing approaches. 。

 

Autobiography: 

Ronald Y. Chang (張佑榕) received the B.S. degree in electrical engineering from National Tsing Hua University in 2000, the M.S. degree in electronics engineering from National Chiao Tung University in 2002, and the Ph.D. degree in electrical engineering from the University of Southern California in 2008. He is currently a Research Fellow (Professor) at CITI, Academia Sinica. He currently serves as an Associate Editor for IEEE Wireless Communications Letters, IEEE Access, and APSIPA Transactions on Signal and Information Processing.