3

PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
Personalized Federated Learning (pFL) has emerged as a promising solution to tackle data heterogeneity across clients in FL. However, …
Chulin Xie, De-An Huang, Wenda Chu, Daguang Xu, Chaowei Xiao, Bo Li, Anima Anandkumar
COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks
Multi-sensor fusion systems (MSF) are widely deployed in modern autonomous vehicles (AVs) as the perception module. Hence, their …
Zijian Huang, Wenda Chu, Linyi Li, Chejian Xu, Bo Li
FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
Federated learning (FL) provides an effective paradigm to train machine learning models over distributed data with privacy protection. …
Wenda Chu, Chulin Xie, Boxin Wang, Linyi Li, Lang Yin, Han Zhao, Bo Li
PDF arxiv