Federated Continual Learning with Weighted Inter-client TransferDownload PDF

12 Jun 2020 (modified: 13 Jul 2020)ICML 2020 Workshop LifelongML Blind SubmissionReaders: Everyone
  • Student First Author: Yes
  • Keywords: Continual Learning, Federated Learning, Deep Learning
  • Abstract: There has been a surge of interest in continual learning and federated learning, both of which are important in deep neural networks in real-world scenarios. Yet little research has been done regarding the scenario where each client learns on a sequence of tasks from private local data stream. This problem of federated continual learning poses new challenges to continual learning, such as utilizing knowledge from other clients, while preventing interference from irrelevant knowledge. To resolve these issues, we propose a novel federated continual learning framework, Weighted Inter-client Transfer (FedWeIT), which decomposes the network weights into global federated parameters and sparse task-specific parameters, and each client receives selective knowledge from other clients by taking a weighted combination of their task-specific parameters. FedWeIT minimizes interference between incompatible tasks, and also allows positive knowledge transfer across clients during learning. We validate our FedWeIT against existing federated learning and continual learning methods under varying degree of task similarity across clients, and our model significantly outperforms them with large reduction in the communication cost.
  • TL;DR: We introduce a new problem of Federated Continual Learning (FCL), where multiple models continuously learn on distributed clients, which poses new challenges such as prevention of inter-client interference and inter-client knowledge transfer.
0 Replies