66 citations · 116 across the 18 of their papers we have counts for
3 papers · 1 filter
Data-Free Knowledge Distillation for Heterogeneous Federated Learning
Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data…
Federated Robustness Propagation: Sharing Robustness in Heterogeneous Federated Learning
Junyuan Hong, Haotao Wang, Zhangyang Wang +1
Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without sharing raw data. One major challenge of FL c…
Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent
Junyuan Hong, Zhangyang Wang, Jiayu Zhou
Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (…