公开(公告)号：US20240320513A1

公开(公告)日：2024-09-26

申请号：US18731260

申请日：2024-06-01

Applicant: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

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

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: 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.

公开(公告)号：US20240320514A1

公开(公告)日：2024-09-26

申请号：US18732399

申请日：2024-06-03

Applicant: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

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

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: 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：US20230112462A1

公开(公告)日：2023-04-13

申请号：US17623247

申请日：2021-08-09

Applicant: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

Inventor： Qi LI ,  Zhenan SUN ,  Yuhao ZHU

IPC: G11B27/031 ,  G06V20/40 ,  G06V40/16 ,  G06V10/26 ,  G06V20/70 ,  G06V10/774 ,  G06V10/80

Abstract: A video generation method includes: obtaining a target face image and a source face image; extracting a feature of each of the source face image and the target face image through a face feature encoder, to obtain corresponding source feature codes and target feature codes; generating swapped face feature codes through a face feature exchanger according to the source feature codes and the target feature codes; generating an initial swapped face image through a face generator according to the swapped face feature codes; and fusing the initial swapped face image with the target face image through a face fuser, to obtain a final swapped face image. The face feature encoder performs hierarchical encoding on the face feature to reserve semantic details of a face, and the face feature exchanger performs further processing based on the hierarchical encoding, to obtain hierarchical encoding of a swapped face feature with semantic details.