Federated Continual Learning with Weighted Inter-client Transfer

Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12073-12086, 2021.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-yoon21b, title = {Federated Continual Learning with Weighted Inter-client Transfer}, author = {Yoon, Jaehong and Jeong, Wonyong and Lee, Giwoong and Yang, Eunho and Hwang, Sung Ju}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {12073--12086}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/yoon21b/yoon21b.pdf}, url = {https://proceedings.mlr.press/v139/yoon21b.html}, 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.} }
Endnote
%0 Conference Paper %T Federated Continual Learning with Weighted Inter-client Transfer %A Jaehong Yoon %A Wonyong Jeong %A Giwoong Lee %A Eunho Yang %A Sung Ju Hwang %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-yoon21b %I PMLR %P 12073--12086 %U https://proceedings.mlr.press/v139/yoon21b.html %V 139 %X 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.
APA
Yoon, J., Jeong, W., Lee, G., Yang, E. & Hwang, S.J.. (2021). Federated Continual Learning with Weighted Inter-client Transfer. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:12073-12086 Available from https://proceedings.mlr.press/v139/yoon21b.html.

Related Material