GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations

TL;DR

GAL enables multiple organizations to collaboratively improve supervised learning models without sharing sensitive data, models, or objectives, by iteratively fitting gradients to optimize a combined loss function.

Contribution

The paper introduces Gradient Assisted Learning (GAL), a novel decentralized method allowing organizations to collaborate on supervised learning without data sharing.

Findings

GAL achieves near-centralized performance in experiments.

GAL preserves data privacy while enabling collaborative learning.

Theoretical analysis confirms convergence of GAL.

Abstract

Collaborations among multiple organizations, such as financial institutions, medical centers, and retail markets in decentralized settings are crucial to providing improved service and performance. However, the underlying organizations may have little interest in sharing their local data, models, and objective functions. These requirements have created new challenges for multi-organization collaboration. In this work, we propose Gradient Assisted Learning (GAL), a new method for multiple organizations to assist each other in supervised learning tasks without sharing local data, models, and objective functions. In this framework, all participants collaboratively optimize the aggregate of local loss functions, and each participant autonomously builds its own model by iteratively fitting the gradients of the overarching objective function. We also provide asymptotic convergence analysis and practical case studies of GAL. Experimental studies demonstrate that GAL can achieve performance close to centralized learning when all data, models, and objective functions are fully disclosed.