公开(公告)号：US20220237508A1

公开(公告)日：2022-07-28

申请号：US17161224

申请日：2021-01-28

申请人： Kiarash SHALOUDEGI ,  Rasul TUTUNOV ,  Haitham BOU AMMAR

发明人： Kiarash SHALOUDEGI ,  Rasul TUTUNOV ,  Haitham BOU AMMAR

IPC分类号： G06N20/00 ,  G06K9/62 ,  G06F17/16 ,  G06F17/15

摘要： Servers, methods and systems for second order federated learning (FL) are described. Client nodes send local curvature information to the server along with local learned parameter information. The local curvature information enables the server to approximate or estimate the curvature, i.e. a second-order derivative, of an objective function of each respective local model. Instead of averaging the local learned parameter information obtained from the client nodes, the server uses the local curvature information to aggregate the local learned parameter information obtained from each client node to correct for the bias that would ordinarily result from a straightforward averaging of the learned values of the local learnable parameters. The described examples may provide reduced bias and/or reduced communication costs, relative to existing FL approaches such as federated averaging. The described examples may provide greater accuracy in model performance and/or faster convergence in FL.