Sponsored by the Data Science Center, the purpose of the Data Science Seminar is to foster collaborations between the core Data Science faculty (CSE/ECE/STAT) and faculty from other sciences that face Data Science problems in their research. After the talk, there will be time for discussions.
The talk will be given by Prof. Basak Guler, Department of Electrical and Computer Engineering, UCR
TITLE:
Scalable Privacy-Aware Collaborative Learning
ABSTRACT:
Privacy-preserving collaborative learning allows multiple data-owners to jointly train machine learning models while keeping their individual datasets private from each other. The main bottleneck against the scalability of such systems to a large number of participants is their communication cost. In this talk, we will introduce novel distributed training frameworks that can achieve scalability and privacy-protection simultaneously. The proposed frameworks provide strong information-theoretic privacy guarantees against (computationally) unbounded adversaries, while achieving significant reduction in the communication overhead against state-of-the-art secure training protocols.
*** Pizza and refreshments will be provided! ***
