Privacy-preserving Federated Clustering and Classification by CVX Optimization (CVXopt) or AI-aided CVXopt

讲座名称：Privacy-preserving Federated Clustering and Classification by CVX Optimization (CVXopt) or AI-aided CVXopt

讲座人：祁忠勇 教授

讲座时间：4月22日15:30-17：30

地点：新科技楼1012报告厅

讲座人介绍：

祁忠勇，1983年于美国南加州大学University of Southern California取得电气工程专业博士学位，1983~1988年任职于美国喷气推进实验室（Jet Propulsion Laboratory, JPL），1989年至今在台湾清华大学电机工程系担任正教授。已发表学术论文170余篇（其中期刊论文60余篇，大部分为IEEE Transactions Signal Processing长文）、专著2本、会议论文100余篇。研究方向广泛，主要包括无线通讯信号处理、凸函数分析及优化、盲信号分离、医学及高光谱影像分析等。祁教授是信号处理领域国际知名学者，为IEEE Senior Member，曾担任IEEE SPAWC、SPC等多个学术会议主席，为IEEE Transactions on Signal Processing、IEEE Transactions on Circuits and Systems I、IEEE Transactions on Circuits and Systems II、IEEE Signal Processing Letters等SCI学术期刊副主编、担任EURASIP Signal Processing编委会成员等。

讲座内容：

Abstract: Federated learning (FL) has been a rapidly growing research area together with artificial intelligence (AI), where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients’ data. In this presentation, by means of the widely known differential privacy (DP) theory for privacy preservation, we present a supervised classification algorithm by AI-aided convex optimization (CVXopt) and an unsupervised clustering algorithm by CVXopt, each developed by solving a non-convex and non-smooth (NCNM) FL problem. Their unique insightful properties and some privacy and convergence analyses are also presented, that can be used for the FL algorithm design guidelines. Extensive experiments on real-world data are presented to demonstrate the effectiveness of the presented algorithms and much superior performance over state-of-the-art FL algorithms, together with the validation of all the analytical results and properties. Finally, we draw some conclusions as well as some future research explorations.

主办单位：通信工程学院