A distillation-based approach integrating continual learning and federated learning for pervasive services

TL;DR

This paper proposes a distillation-based method to address catastrophic forgetting in federated learning, specifically applied to Human Activity Recognition, enhancing continual learning for pervasive edge devices.

Contribution

It introduces a novel distillation approach integrating continual and federated learning tailored for pervasive services, addressing domain-specific challenges.

Findings

Effective mitigation of catastrophic forgetting in federated learning

Improved performance on Human Activity Recognition tasks

Demonstrates applicability to pervasive edge device scenarios

Abstract

Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be adapted to the specificity of the pervasive domain. In particular, issues related to continual learning need to be addressed. In this paper, we present a distillation-based approach dealing with catastrophic forgetting in federated learning scenario. Specifically, Human Activity Recognition tasks are used as a demonstration domain.