A distillation-based approach integrating continual learning and federated learning for pervasive services
This addresses the need for adapting federated learning to handle continual learning issues in pervasive domains like smart services, but it appears incremental as it combines existing techniques.
The paper tackles the problem of catastrophic forgetting in federated learning for pervasive services, proposing a distillation-based approach and demonstrating it on Human Activity Recognition tasks.
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.