公开(公告)号：US20230074417A1

公开(公告)日：2023-03-09

申请号：US18055149

申请日：2022-11-14

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Ji LIU ,  Sunjie YU ,  Jiwen ZHOU ,  Ruipu ZHOU ,  Dejing DOU

IPC: G06N3/08 ,  G06N3/04

Abstract: A method for training a longitudinal federated learning model is provided, and is applied to a first participant device. The first participant device includes label data. The longitudinal federated learning model includes a first bottom layer sub-model, an interaction layer sub-model, a top layer sub-model based on a Lipschitz neural network and a second bottom layer sub-model in a second participant device. First bottom layer output data of the first participant device and second bottom layer output data sent by the second participant device are obtained. The first bottom layer output data and the second bottom layer output data are input into an interaction layer sub-model to obtain interaction layer output data. Top layer output data is obtained based on the interaction layer output data and the top layer sub-model. The longitudinal federated learning model is trained according to the top layer output data and the label data.

公开(公告)号：US20230083116A1

公开(公告)日：2023-03-16

申请号：US17988264

申请日：2022-11-16

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Ji LIU ,  Hong ZHANG ,  Juncheng JIA ,  Jiwen ZHOU ,  Shengbo PENG ,  Ruipu ZHOU ,  Dejing DOU

IPC: G06N20/00 ,  G06F9/54

Abstract: A federated learning method and system, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of computer vision and deep learning technologies. The method includes: performing a plurality of rounds of training until a training end condition is met, to obtain a trained global model; and publishing the trained global model to a plurality of devices. Each of the plurality of rounds of training includes: transmitting a current global model to at least some devices in the plurality of devices; receiving trained parameters for the current global model from the at least some devices; performing an aggregation on the received parameters to obtain a current aggregation model; and adjusting the current aggregation model based on a globally shared dataset, and updating the adjusted aggregation model as a new current global model for a next round of training.

公开(公告)号：US20220374776A1

公开(公告)日：2022-11-24

申请号：US17868113

申请日：2022-07-19

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ji LIU ,  Beichen MA ,  Chendi ZHOU ,  Jingbo ZHOU ,  Ruipu ZHOU ,  Dejing DOU

IPC: G06N20/00

Abstract: The present disclosure provides a method and apparatus for federated learning, which relate to the technical fields such as big data and deep learning. A specific implementation is: generating, for each task in a plurality of different tasks trained simultaneously, a global model for each task; receiving resource information of each available terminal in a current available terminal set; selecting a target terminal corresponding to each task from the current available terminal set, based on the resource information and the global model; and training the global model using the target terminal until a trained global model for each task meets a preset condition.

公开(公告)号：US20220374775A1

公开(公告)日：2022-11-24

申请号：US17867516

申请日：2022-07-18

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ji LIU ,  Beichen MA ,  Jingbo ZHOU ,  Ruipu ZHOU ,  Dejing DOU

IPC: G06N20/00 ,  G06F9/48

Abstract: A method for multi-task scheduling, a device and a storage medium are provided. The method may include: initializing a list of candidate scheduling schemes, the candidate scheduling scheme being used to allocate a terminal device for training to each machine learning task in a plurality of machine learning tasks; perturbing, for each candidate scheduling scheme in the list of candidate scheduling schemes, the candidate scheduling scheme to generate a new scheduling scheme; determining whether to replace the candidate scheduling scheme with the new scheduling scheme based on a fitness value of the candidate scheduling scheme and a fitness value of the new scheduling scheme, to generate a new scheduling scheme list; and determining a target scheduling scheme, based on the fitness value of each new scheduling scheme in the new scheduling scheme list.

公开(公告)号：US20240086717A1

公开(公告)日：2024-03-14

申请号：US18098514

申请日：2023-01-18

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ji LIU ,  Hao TIAN ,  Ruipu ZHOU ,  Dejing DOU

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: Disclosed is a model training control method based on asynchronous federated learning, an electronic device and a storage medium, relating to data processing technical field, and especially to technical fields such as edge computing and machine learning. The method includes: sending a first parameter of a first global model to a plurality of edge devices; receiving a second parameter of a second global model returned by a first edge device of plurality of edge devices, the second global model being a global model obtained after the first edge device trains the first global model according to a local data set; and sending a third parameter of a third global model to a second edge device of the plurality of edge devices in a case of the third global model is obtained based on aggregation of at least one second global model.

公开(公告)号：US20230206123A1

公开(公告)日：2023-06-29

申请号：US18080803

申请日：2022-12-14

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Ji LIU ,  Hong ZHANG ,  Juncheng JIA ,  Ruipu ZHOU ,  Dejing DOU

IPC: G06N20/00 ,  G06F9/48

CPC classification number: G06N20/00 ,  G06F9/4881

Abstract: A technical solution relates to distributed machine learning, and relates to the field of artificial intelligence technologies, such as machine learning technologies, or the like. An implementation includes: acquiring, based on delay information, an optimal scheduling queue of a plurality of edge devices participating in training; and scheduling each edge device of the plurality of edge devices to train a machine learning model based on the optimal scheduling queue of the plurality of edge devices.

公开(公告)号：US20220385583A1

公开(公告)日：2022-12-01

申请号：US17817594

申请日：2022-08-04

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Ji LIU ,  Jiayuan ZHANG ,  Ruipu ZHOU ,  Dejing DOU

IPC: H04L47/22 ,  H04L47/2475

Abstract: A traffic classification method and apparatus, a training method and apparatus, a device and a medium are provided. An implementation is: performing a preprocessing operation on each characteristic of one or more characteristics of an object to be classified; and inputting the one or more characteristics of the object to be classified into a traffic classifier to determine a traffic type of the object to be classified. The preprocessing operation includes at least one of: setting, in response to determining that a characteristic value of the characteristic is invalid data, the characteristic value to a null value; converting, in response to determining that the characteristic is a non-numeric characteristic, the characteristic value of the characteristic to an integer value, and normalizing, in response to determining that the characteristic is a non-port characteristic, the characteristic value of the characteristic.