Federated Continual Learning with Weighted Inter-client Transfer

TL;DR

FedWeIT is a novel federated continual learning framework that decomposes network weights to enable positive knowledge transfer across clients while minimizing interference, significantly improving performance and reducing communication costs.

Contribution

Introduces FedWeIT, a framework that combines weight decomposition and selective knowledge transfer for federated continual learning, addressing interference and transfer challenges.

Findings

FedWeIT outperforms existing methods in accuracy across various tasks.

Significant reduction in communication costs with FedWeIT.

Effective knowledge transfer across clients with minimal interference.

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. 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 degrees of task similarity across clients, and our model significantly outperforms them with a large reduction in the communication cost. Code is available at https://github.com/wyjeong/FedWeIT