An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning

Excerpt

arXiv:2608.15153v1 Announce Type: cross Abstract: Differentially private federated learning must balance privacy protection against model accuracy and training efficiency. Static gradient clipping applies a fixed threshold throughout training and across model layers, which can cause excessive clipping when the threshold is too small or unnecessarily large noise when it is too large. This paper presents DDP-SA-adaptive, an adaptive gradient clipping and noise adding mechanism for differentially p