tinyML On Device Learning Forum – Yiran Chen: Scalable, Heterogeneity-Aware and Trustworthy…

Scalable, Heterogeneity-Aware and Trustworthy Federated Learning
Yiran CHEN, Professor, Duke University

Federated learning has become a popular distributed machine learning paradigm for developing on-device AI applications. However, the data residing on the devices is intrinsically statistically heterogeneous (i.e., non-IID data distribution) and the mobile devices usually have limited communication bandwidth to transfer local updates. Such statistical heterogeneity and communication limitation are two major bottlenecks that hinder applying federated learning in practice. In addition, recent works have demonstrated that sharing model updates makes federated learning vulnerable to inference attacks and model poisoning attacks. In this talk, we will present our recent works on novel federated learning frameworks to address the scalability and heterogeneity issues simultaneously. In addition, we will also reveal the essential reason of privacy leakage and model poisoning attacks in federated learning procedures, and provide the defense mechanisms accordingly towards trustworthy federated learning.

source