Privacy-Preserving Heterogeneous Federated Learning: A Survey

PhD Qualifying Examination


Title: "Privacy-Preserving Heterogeneous Federated Learning: A Survey"

by

Mr. Dashan Gao


Abstract:

Artificial intelligence (AI) has achieved tremendous success and is widely 
applied to numerous areas, thanks to the advances in AI research and the surge 
of big data. However, there has been growing awareness and concerns about data 
scarcity and privacy. Due to various legal and political privacy restrictions, 
data could be dispersed over different organizations and cannot be transmitted. 
Federated learning (FL) is proposed to protect data privacy and virtually 
assemble the isolated data silos by cooperatively training models among 
organizations without breaching privacy and security. However, FL faces 
heterogeneity from various aspects, including data space, statistical, and 
system heterogeneity. For example, collaborative organizations without conflict 
of interest often come from different areas and have heterogeneous data from 
different feature spaces. Participants may also want to train heterogeneous 
personalized local models due to non-IID and imbalanced data distribution and 
various resource-constrained devices. Therefore, heterogeneous FL is proposed 
to address the problem of heterogeneity in FL.

In this survey, we comprehensively investigate the domain of heterogeneous FL 
in terms of data space, statistical, system, and model heterogeneity. We first 
introduce FL, including its definition and categorization. We also present some 
privacy and security techniques for privacy-preserving FL. Then, We propose a 
precise taxonomy of heterogeneous FL settings for each type of heterogeneity 
according to the problem setting and learning objective. We also investigate 
the transfer learning methodologies to tackle the heterogeneity in FL. We 
further present the applications of heterogeneous FL. Finally, we highlight the 
challenges and opportunities and envision promising future research directions 
toward new framework design and trustworthy approaches.


Date:  			Friday, 26 August 2022

Time:                  	11:00 am - 12:00 noon

Zoom Meeting:    	https://hkust.zoom.us/j/9715764970

Committee Members:	Prof. Qiang Yang (Supervisor)
 			Prof. Kai Chen (Chairperson)
 			Prof. Qiong Luo
 			Prof. Yangqiu Song


**** ALL are Welcome ****