报告题目：Federated Continual Learning

报 告 人：吴大鹏（香港城市大学讲座教授）

主 持 人：许勇教授

报告时间：2024年9月18日（星期三）上午10:30—11:30

报告地点：华南理工大学广州国际校区D1-b110

欢迎广大师生参加！

广州国际校区综合事务办公室

广州国际校区学生事务办公室

2024年9月15日

报告人简介：

吴大鹏教授曾获佛罗里达大学终身教授奖、佛罗里达大学研究基金会教授奖、AFOSR青年研究者计划奖(YIP)、ONR青年研究者计划奖(YIP)、NSF CAREER奖、IEEE电路与系统视频技术(CSVT)交易最佳论文奖、GLOBECOM最佳论文奖和QShine最佳论文奖，曾担任《人工智能学报》、《多媒体进展杂志》的创始主编、《IEEE网络科学与工程学报》主编、《IEEE通信学会开放杂志》特约编辑以及《IEEE云计算学报》、《IEEE通信学报》、《IEEE网络信号与信息处理学报》、《IEEE信号处理杂志》的副主编，曾担任IEEE INFOCOM 2012技术计划委员会(TPC)主席，于2016年被IEEE车辆技术学会选为杰出讲师。

报告摘要：

The goal of federated learning is to preserve data privacy when training Artificial Intelligence (AI) systems, while continual learning is to enable an AI system to acquire new skills without forgetting old skills.  To combine the capabilities of federated learning and continual learning, federated continual learning (FCL) arises.  But before FCL can enjoy the benefits of both federated learning and continual learning, FCL needs to be able to effectively transfer knowledge across different clients and across various tasks. Current FCL methods mainly focus on avoiding interference between tasks, thereby overlooking the potential of knowledge transfer across tasks learned by different clients in separated time intervals. To address this issue, in this talk, I will present a Prompt-based Knowledge Transfer FCL algorithm, to effectively foster the transfer of knowledge encapsulated in prompts between various sequentially learned tasks and clients.