Federated Continual Learning with Weighted Inter-client Transfer

       Jaehong Yoon 1 * Wonyong Jeong 1 2 * Giwoong Lee 1 Eunho Yang 1 2 Sung Ju Hwang 1 2

             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 lo-
   cal data stream. ...