Global Update Guided Federated Learning

04/08/2022
by   Qilong Wu, et al.
0

Federated learning protects data privacy and security by exchanging models instead of data. However, unbalanced data distributions among participating clients compromise the accuracy and convergence speed of federated learning algorithms. To alleviate this problem, unlike previous studies that limit the distance of updates for local models, we propose global-update-guided federated learning (FedGG), which introduces a model-cosine loss into local objective functions, so that local models can fit local data distributions under the guidance of update directions of global models. Furthermore, considering that the update direction of a global model is informative in the early stage of training, we propose adaptive loss weights based on the update distances of local models. Numerical simulations show that, compared with other advanced algorithms, FedGG has a significant improvement on model convergence accuracies and speeds. Additionally, compared with traditional fixed loss weights, adaptive loss weights enable our algorithm to be more stable and easier to implement in practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/27/2022

AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation

In an asynchronous federated learning framework, the server updates the ...
research
05/23/2022

Semi-Decentralized Federated Learning with Collaborative Relaying

We present a semi-decentralized federated learning algorithm wherein cli...
research
03/28/2023

On the Local Cache Update Rules in Streaming Federated Learning

In this study, we address the emerging field of Streaming Federated Lear...
research
06/17/2022

Avoid Overfitting User Specific Information in Federated Keyword Spotting

Keyword spotting (KWS) aims to discriminate a specific wake-up word from...
research
12/03/2020

Robust Federated Learning with Noisy Labels

Federated learning is a paradigm that enables local devices to jointly t...
research
08/24/2023

FedSoL: Bridging Global Alignment and Local Generality in Federated Learning

Federated Learning (FL) aggregates locally trained models from individua...
research
05/03/2022

Revisiting Communication-Efficient Federated Learning with Balanced Global and Local Updates

In federated learning (FL), a number of devices train their local models...

Please sign up or login with your details

Forgot password? Click here to reset