In federated learning, the non-independent and identically distributed(non-IID) data across clients leads to slower convergence of the global model and significantly increases communication costs. Existing methods collect information about the label distribution of clients to determine aggregation weights for local models, accelerating convergence, but this may leak clients' privacy. To address the slower convergence caused by non-IID data without leaking clients' privacy, this paper proposed the FedNA aggregation algorithm. FedNA achieved this goal in two ways. Firstly, it assigned aggregation weights based on the L₁ norm of the class weight updates of local models to retain their contributions. Secondly, it set the class weight updates corresponding to missing classes at the clients to 0 to mitigate their impact on aggregation. Experiments were conducted under four different data distributions on two datasets. The results show that compared to FedAvg, the FedNA algorithm can reduce the number of iterations required to reach steady state by 890 at best, lowering communication costs by 44.5%. FedNA maintains clients' privacy while accelerating the convergence of the global model and decreasing communication costs. It is suitable for situations that need to protect clients privacy and are sensitive to communication efficiency.

[2023-11-01] Accepted Paper /doc/2023.07.0327/v1

[2024-03-05] Printed Article /doc/2023.07.0327/v2