Federated and continual learning for classification tasks in a society of devices

TL;DR

This paper introduces LFedCon2, a lightweight federated and continual learning framework enabling resource-constrained devices like smartphones to learn and improve models collaboratively over time, addressing privacy and concept drift.

Contribution

The work presents a novel lightweight federated and continual learning architecture suitable for non-dedicated devices, handling evolving data distributions and privacy concerns.

Findings

LFedCon2 outperforms existing methods in walking recognition accuracy.

The approach enables real-time, autonomous learning on smartphones.

Models improve globally through collaborative local updates.

Abstract

Today we live in a context in which devices are increasingly interconnected and sensorized and are almost ubiquitous. Deep learning has become in recent years a popular way to extract knowledge from the huge amount of data that these devices are able to collect. Nevertheless, centralized state-of-the-art learning methods have a number of drawbacks when facing real distributed problems, in which the available information is usually private, partial, biased and evolving over time. Federated learning is a popular framework that allows multiple distributed devices to train models remotely, collaboratively, and preserving data privacy. However, the current proposals in federated learning focus on deep architectures that in many cases are not feasible to implement in non-dedicated devices such as smartphones. Also, little research has been done regarding the scenario where data distribution changes over time in unforeseen ways, causing what is known as concept drift. Therefore, in this work we want to present Light Federated and Continual Consensus (LFedCon2), a new federated and continual architecture that uses light, traditional learners. Our method allows powerless devices (such as smartphones or robots) to learn in real time, locally, continuously, autonomously and from users, but also improving models globally, in the cloud, combining what is learned locally, in the devices. In order to test our proposal, we have applied it in a heterogeneous community of smartphone users to solve the problem of walking recognition. The results show the advantages that LFedCon2 provides with respect to other state-of-the-art methods.