Approaches to address the data skew problem in federated learning

Dinesh C. Verma; Graham White; Simon Julier; Stepehen Pasteris; Supriyo Chakraborty; Greg Cirincione

doi:10.1117/12.2519621

10 May 2019 Approaches to address the data skew problem in federated learning

Dinesh C. Verma, Graham White, Simon Julier, Stepehen Pasteris, Supriyo Chakraborty, Greg Cirincione

Proceedings Volume 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications; 110061I (2019) https://doi.org/10.1117/12.2519621
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

A Federated Learning approach consists of creating an AI model from multiple data sources, without moving large amounts of data across to a central environment. Federated learning can be very useful in a tactical coalition environment, where data can be collected individually by each of the coalition partners, but network connectivity is inadequate to move the data to a central environment. However, such data collected is often dirty and imperfect. The data can be imbalanced, and in some cases, some classes can be completely missing from some coalition partners. Under these conditions, traditional approaches for federated learning can result in models that are highly inaccurate. In this paper, we propose approaches that can result in good machine learning models even in the environments where the data may be highly skewed, and study their performance under different environments.

Conference Presentation

Citation Download Citation

Dinesh C. Verma, Graham White, Simon Julier, Stepehen Pasteris, Supriyo Chakraborty, and Greg Cirincione "Approaches to address the data skew problem in federated learning", Proc. SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 110061I (10 May 2019); https://doi.org/10.1117/12.2519621

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available