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

Anastasiya Danilenka; Jacek Ma\'ndziuk; Marcin Paprzycki; Maria Ganzha

REVIEW

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.08124 v1 pith:IB6LU7PE submitted 2022-06-16 cs.LG

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

Anastasiya Danilenka , Maria Ganzha , Marcin Paprzycki , Jacek Ma\'ndziuk This is my paper

classification cs.LG

keywords adversarialdatafederateddealinputslabellearningnon-iid

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

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.

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

discussion (0)