Federated Continual Learning with Weighted Inter-client Transfer

Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang

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 a 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, Federated 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.FedWeITminimizes interference between incompatible tasks, and also allows positive knowledge transfer across clients during learning. We validate ourFedWeITagainst existing federated learning and continual learning methods under varying degrees of task similarity across clients, and our model significantly outperforms them with a large reduction in the communication cost.

One-sentence Summary: We define a problem of federated continual learning and propose a novel federated continual learning framework, Weighted Inter-client Transfer (FedWeIT).

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=sIxnjBZzr