公开(公告)号：US20240320514A1

公开(公告)日：2024-09-26

申请号：US18732399

申请日：2024-06-03

申请人： INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

发明人： Zhenan SUN ,  Yunlong WANG ,  Zhengquan LUO ,  Kunbo ZHANG ,  Qi LI ,  Yong HE

IPC分类号： G06N3/098

CPC分类号： G06N3/098

摘要： Disclosed is a method for updating a node model that resists discrimination propagation in federated learning. The method includes: obtaining a node model corresponding to a data node; calculating a mean value of the distribution of class features and a quantity ratio corresponding to training data of the data node, calculating a distribution weighted aggregation model based on the node model, the mean value of the distribution of class features and the quantity ratio; calculating a regularization term corresponding to the data node based on the node model and the distribution weighted aggregation model; calculating a variance of the distribution of the class features corresponding to the data node, calculating a class balanced complementary term by using a cross-domain feature generator; and updating the node model based on the distribution weighted aggregation model, the regularization term, and the class balanced complementary term.

公开(公告)号：US20240320513A1

公开(公告)日：2024-09-26

申请号：US18731260

申请日：2024-06-01

申请人： INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

发明人： Zhenan SUN ,  Yunlong WANG ,  Zhengquan LUO ,  Kunbo ZHANG ,  Qi LI ,  Yong HE

IPC分类号： G06N3/098

CPC分类号： G06N3/098

摘要： Disclosed is a disentangled personalized federated learning method via consensus representation extraction and diversity propagation provided by embodiments of the present application. The method includes: receiving, by a current node, local consensus representation extraction models and unique representation extraction models corresponding to other nodes, respectively; extracting, by the current node, the representations of the data of the current node by using the unique representation extraction models of other nodes respectively, and calculating first mutual information between different sets of representation distributions, determining similarity of the data distributions between the nodes based on the size of the first mutual information, and determining aggregation weights corresponding to the other nodes based on the first mutual information; the current node obtains the global consensus representation aggregation model corresponding to the current node.