Federated and continual learning for classification tasks in a society of devices
This work addresses the challenge of real-time, privacy-preserving learning on resource-constrained devices for applications like activity recognition, though it appears incremental by combining existing federated and continual learning approaches.
The authors tackled the problem of enabling lightweight, distributed devices like smartphones to learn collaboratively and continuously from private, evolving data by proposing LFedCon2, a federated and continual learning architecture using traditional learners, which outperformed state-of-the-art methods in walking recognition tasks.
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.