Non-IID data and Continual Learning processes in Federated Learning: A long road ahead

TL;DR

This paper reviews the challenges of data heterogeneity in Federated Learning, classifies different types of non-IID data, and explores strategies from Continual Learning to address these issues.

Contribution

It provides a formal classification of data heterogeneity in Federated Learning and discusses how Continual Learning methods can be adapted to mitigate these challenges.

Findings

Classifies various forms of data heterogeneity in Federated Learning.

Reviews strategies to handle non-IID data in federated settings.

Suggests potential adaptation of Continual Learning techniques for federated scenarios.

Abstract

Federated Learning is a novel framework that allows multiple devices or institutions to train a machine learning model collaboratively while preserving their data private. This decentralized approach is prone to suffer the consequences of data statistical heterogeneity, both across the different entities and over time, which may lead to a lack of convergence. To avoid such issues, different methods have been proposed in the past few years. However, data may be heterogeneous in lots of different ways, and current proposals do not always determine the kind of heterogeneity they are considering. In this work, we formally classify data statistical heterogeneity and review the most remarkable learning strategies that are able to face it. At the same time, we introduce approaches from other machine learning frameworks, such as Continual Learning, that also deal with data heterogeneity and could be easily adapted to the Federated Learning settings.