Paper accepted at CVPRW 2023

Our work “Asynchronous Federated Continual Learning”, has been accepted to be presented at the Federated Learning for Computer Vision (FedVision) Workshop of CVPR 2023, held in Vancouver in June 18-22 2023.

TL;DR: We introduce a novel federated learning setting (AFCL) where the continual learning of multiple tasks happens at each client with different orderings and in asynchronous time slots. To tackle this task, we propose FedSpace which makes use of prototype-based learning, a representation loss, fractal pre-training, and a modified aggregation policy.

Paper: https://arxiv.org/abs/2304.03626

Code: https://github.com/LTTM/FedSpace