公开(公告)号：US20230342669A1

公开(公告)日：2023-10-26

申请号：US18344188

申请日：2023-06-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yunfeng Shao ,  Bingshuai Li ,  Jun Wu ,  Haibo Tian

IPC: G06N20/00 ,  H04L9/00 ,  H04L9/08 ,  H04L9/30

CPC classification number: G06N20/00 ,  H04L9/008 ,  H04L9/088 ,  H04L9/30

Abstract: Embodiments of this application provide a machine learning model update method, applied to the field of artificial intelligence. The method includes: A first apparatus generates a first intermediate result based on a first data subset. The first apparatus receives an encrypted second intermediate result sent by a second apparatus, where the second intermediate result is generated based on a second data subset corresponding to the second apparatus. The first apparatus obtains a first gradient of a first model, where the first gradient of the first model is generated based on the first intermediate result and the encrypted second intermediate result. After being decrypted by using a second private key, the first gradient of the first model is for updating the first model, where the second private key is a decryption key generated by the second apparatus for homomorphic encryption.

公开(公告)号：US20240362361A1

公开(公告)日：2024-10-31

申请号：US18764330

申请日：2024-07-04

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yunfeng Shao ,  Bingshuai Li

IPC: G06F21/62 ,  H04L9/08

CPC classification number: G06F21/6245 ,  H04L9/0816

Abstract: This disclosure provides a user data processing system. A first data processing device in the system generates a first intermediate result, and sends a third intermediate result to a second data processing device. The third intermediate result is obtained from the first intermediate result based on a parameter of a first machine learning model and target historical user data obtained by the first data processing device, and an identifier of the target historical user data is the same as an identifier of historical user data of the second data processing device. The first data processing device further receives a second intermediate result, and updates the parameter of the first machine learning model based on the first intermediate result and the second intermediate result. The second data processing device further updates a parameter of a second machine learning model based on the received third intermediate result and the second intermediate result.

公开(公告)号：US20250156726A1

公开(公告)日：2025-05-15

申请号：US19022480

申请日：2025-01-15

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yunfeng Shao ,  Bingshuai Li ,  Jiaxun Lu ,  Zhenzhe Zheng ,  Fan Wu ,  Dahai Hu

IPC: G06N3/098

Abstract: A federated learning method includes a central node that separately sends a first model to at least one central edge device, receives at least one second model, and aggregates the at least one second model to obtain a fourth model. The at least one central edge device is in one-to-one correspondence with at least one edge device group. The second model is obtained by aggregating a third model respectively obtained by each edge device in at least one edge device group. The third model is obtained by one edge device in collaboration with at least one terminal device in a coverage area through learning the first model based on local data. The edge devices are grouped into edge device groups, and a central edge device in one edge device group sends the first model to each edge device in the edge device group.

公开(公告)号：US20230353347A1

公开(公告)日：2023-11-02

申请号：US18344185

申请日：2023-06-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yunfeng Shao ,  Bingshuai Li ,  Haibo Tian

IPC: H04L9/08 ,  H04L9/00

CPC classification number: H04L9/0836 ,  H04L9/008

Abstract: A first apparatus provides a second apparatus with encrypted label distribution information for the first node, so that the second apparatus calculates an intermediate parameter of a segmentation policy of the second apparatus side based on the encrypted label distribution information, and therefore a gain of the segmentation policy of the second apparatus side can be obtained. A preferred segmentation policy of the first node can also be obtained based on the gain of the segmentation policy of the second apparatus side and a gain of a segmentation policy of the first apparatus side. The encrypted label distribution information includes label data and distribution information, and is in a ciphertext state. The encrypted label distribution information can be used to determine the gain of the segmentation policy without leaking a distribution status of a sample set on the first node.