Using adversarial images to improve outcomes of federated learning for non-IID data

06/16/2022
by   Anastasiya Danilenka, et al.
0

One of the important problems in federated learning is how to deal with unbalanced data. This contribution introduces a novel technique designed to deal with label skewed non-IID data, using adversarial inputs, created by the I-FGSM method. Adversarial inputs guide the training process and allow the Weighted Federated Averaging to give more importance to clients with 'selected' local label distributions. Experimental results, gathered from image classification tasks, for MNIST and CIFAR-10 datasets, are reported and analyzed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/29/2020

Dynamic Federated Learning Model for Identifying Adversarial Clients

Federated learning, as a distributed learning that conducts the training...
research
10/13/2021

WAFFLE: Weighted Averaging for Personalized Federated Learning

In collaborative or federated learning, model personalization can be a v...
research
07/20/2021

Precision-Weighted Federated Learning

Federated Learning using the Federated Averaging algorithm has shown gre...
research
10/26/2021

Ensemble Federated Adversarial Training with Non-IID data

Despite federated learning endows distributed clients with a cooperative...
research
12/02/2019

AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning

We propose a method that enables practitioners to conveniently incorpora...
research
08/01/2023

Data Collaboration Analysis applied to Compound Datasets and the Introduction of Projection data to Non-IID settings

Given the time and expense associated with bringing a drug to market, nu...
research
09/06/2023

Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat

We carefully evaluate a number of algorithms for learning in a federated...

Please sign up or login with your details

Forgot password? Click here to reset