Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification

Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-09
Main Authors: Hsu, Tzu-Ming Harry, Qi, Hang, Brown, Matthew
Format: Article
Language:English
Subjects:
Algorithms
Classification
Electronic devices
Federated learning
Performance degradation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We show that performance degrades as distributions differ more, and propose a mitigation strategy via server momentum. Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings.
ISSN:2331-8422