FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations

arXiv:2302.01068v4 Announce Type: replace
Abstract: Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be attributed to the inconsistency between the local and global objectives. To address this issue, we propose FedLAP-DP, a novel privacy-preserving approach for FL. Our formulation involves clients synthesizing a small set of samples that approximate local loss landscapes by simulating the gradients of …

arxiv cs.lg federated learning loss type