收起
Vincent Wong教授:个性化联邦学习及其在360度视频流媒体中的应用
【引言】
联邦学习是一种允许多个边缘设备协作训练一个模型的分布式人工智能框架,而个性化联邦学习可以解决数据异构性和设备异构性问题。在360度视频流媒体的领域中,个性化联邦学习算法可以用于训练用户的头部移动预测模型,该预测模型是基于内容的视口预测框架中的重要组成部分。
第十二期 IEEE TNSE 杰出讲座系列活动,我们有幸邀请到Vincent Wong教授介绍个性化联邦学习及其在360度视频流媒体中的应用,并分享他在这个领域内的相关研究成果与有趣发现。
执行主席
Executive Chair
黄建伟
香港中文大学(深圳)校长讲座教授、协理副校长
AIRS 副院长兼群体智能中心主任
IEEE TNSE主编
IEEE Fellow
AAIA Fellow
报告嘉宾
Speaker
英属哥伦比亚大学教授
IEEE Fellow
Vincent Wong教授是英属哥伦比亚大学电气与计算机工程系的教授。他的研究领域包括通信网络的协议设计、优化和资源管理,涉及到互联网、无线网络、智能电网、移动边缘计算和物联网等应用。目前,Vincent Wong教授担任IEEE TWC的主编。2016年,他获评IEEE fellow。
Personalized Federated Learning and Its Application in 360-degree Video Streaming
Title: Personalized Federated Learning and Its Application in 360-degree Video Streaming
Abstract: Federated learning is a distributed artificial intelligence framework, which allows multiple edge devices to train a single model collaboratively. In this talk, we first introduce a personalized federated learning algorithm which can tackle the issues of data heterogeneity and device heterogeneity. Then, we present a content-based viewport prediction framework for 360-degree video streaming, wherein users’ head movement prediction models are trained using a personalized federated learning algorithm. The output of the viewport prediction framework corresponds to which video tiles to be transmitted. Finally, we present an algorithm to determine the bitrate and beamforming matrices in a THz-enabled 360-degree video streaming system with multiple access points.
Bio: Vincent Wong is a Professor in the Department of Electrical and Computer Engineering at the University of British Columbia, Vancouver, Canada. His research areas include protocol design, optimization, and resource management of communication networks, with applications to the Internet, wireless networks, smart grid, mobile edge computing, and Internet of Things. Currently, Dr. Wong is the Editor-in-Chief of the IEEE Transactions on Wireless Communications. He is a Fellow of the IEEE.
*特别鸣谢叶文涛提供相关内容
(10个月前)
(10个月前)
(10个月前)
(10个月前)
(10个月前)
(10个月前)
1、本活动具体服务及内容由主办方【AIRS 研究院】提供,活动行仅提供票务技术支持,请仔细阅读活动内容后参与。
2、如在活动参与过程中遇到问题或纠纷,双方应友好协商沟通,也可联络活动行进行协助。