Federated Learning with Data-Agnostic Distribution Fusion

no code implementations • CVPR 2023 • Jian-hui Duan, Wenzhong Li, Sanglu Lu

In this paper, we propose a novel data-agnostic distribution fusion based model aggregation method called \texttt{FedDAF} to optimize federated learning with non-IID local datasets, based on which the heterogeneous clients' data distributions can be represented by the fusion of several virtual components with different parameters and weights.

Federated Learning

Federated Learning with Decoupled Probabilistic-Weighted Gradient Aggregation

no code implementations • 1 Jan 2021 • Jian-hui Duan, Wenzhong Li, Sanglu Lu

In this paper, we proposed a novel decoupled probabilistic-weighted gradient aggregation approach called FeDEC for federated learning.

Federated Learning Variational Inference