-
公开(公告)号：US20220391780A1
公开(公告)日：2022-12-08
申请号：US17820758
申请日：2022-08-18
Inventor： Ji LIU , Beichen MA , Chendi ZHOU , Juncheng JIA , Dejing DOU , Shilei JI , Yuan LIAO
Abstract: The present disclosure provides a method of federated learning. A specific implementation solution includes: determining, for a current learning period, a target device for each task of at least one learning task to be performed, from a plurality of candidate devices according to a plurality of resource information of the plurality of candidate devices; transmitting a global model for the each task to the target device for the each task, so that the target device for the each task trains the global model for the each task; and updating, in response to receiving trained models from all target devices for the each task, the global model for the each task according to the trained models, so as to complete the current learning period. The present disclosure further provides an electronic device, and a storage medium.
-
12.发明申请公开(公告)号：US20220374776A1
公开(公告)日：2022-11-24
申请号：US17868113
申请日：2022-07-19
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
Inventor： Ji LIU , Beichen MA , Jingbo ZHOU , Ruipu ZHOU , Dejing DOU
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：US20220366320A1
公开(公告)日：2022-11-17
申请号：US17864098
申请日：2022-07-13
Inventor： Ji LIU , Chendi ZHOU , Juncheng JIA , Dejing DOU
IPC: G06N20/20
Abstract: A computer-implemented method is provided. The method includes: executing, for each task in a federated learning system, a first training process comprising: obtaining resource information of a plurality of terminal devices of the federated learning system; determining one or more target terminal devices corresponding to the task based on the resource information; and training a global model corresponding to the task by the target terminal devices until the global model meets a preset condition.
-
公开(公告)号：US20220237474A1
公开(公告)日：2022-07-28
申请号：US17721659
申请日：2022-04-15
Inventor： Yanyan LI , Jingbo ZHOU , Jizhou HUANG , Dejing DOU
IPC: G06N5/02 , G06F16/901
Abstract: A method and apparatus for semanticization is provided. The method includes: ascertaining a target coordinate of a to-be-semanticized location; ascertaining, through a pre-built regional spatial index tree, a target region to which the target coordinate of the to-be-semanticized location belongs; and ascertaining semantic information of the to-be-semanticized location based on semantic information of the target region.
-
Patent Agency Ranking
公开(公告)号：US20220222278A1
公开(公告)日：2022-07-14
申请号：US17706706
申请日：2022-03-29
Inventor： Xinjiang LU , Dejing DOU
IPC: G06F16/28
Abstract: The present disclosure provides a region information processing method and apparatus, and relates to the field of artificial intelligence in computer technologies. The specific implementation is: acquiring a first distance between a first region and a second region, a first object set included in the first region, and a second object set included in the second region; determining spatial dependency information between the first region and the second region according to the first distance; determining object dependency information between the first region and the second region according to the first object set and the second object set; and determining a symbiosis between the first region and the second region according to the spatial dependency information and the object dependency information.
-
公开(公告)号：US20220101199A1
公开(公告)日：2022-03-31
申请号：US17531132
申请日：2021-11-19
Inventor： Hao LIU , Weijia ZHANG , Dejing DOU , Hui XIONG
IPC: G06N20/00
Abstract: A training method for a point-of-interest recommendation model and a method for recommending a point of interest are provided. An implementation solution includes: obtaining training data including a plurality of point-of-interest recommendation requests; determining initialization parameters of the point-of-interest recommendation model; for a first point-of-interest recommendation request among the plurality of point-of-interest recommendation requests, determining a current return for the first point-of-interest recommendation request by utilizing the point-of-interest recommendation model, and determining, based on a second point-of-interest recommendation request initiated after the first point-of-interest recommendation request is completed, a target return for the first point-of-interest recommendation request by utilizing the point-of-interest recommendation model; and adjusting the initialization parameters of the point-of-interest recommendation model based on a difference between the current return and the target return for the first point-of-interest recommendation request, to obtain final parameters of the point-of-interest recommendation model.
-
18.发明申请公开(公告)号：US20220092433A1
公开(公告)日：2022-03-24
申请号：US17457903
申请日：2021-12-06
Inventor： Hao LIU , Jindong HAN , Hengshu ZHU , Dejing DOU
Abstract: Provided are a training method and device for a heterogeneous generative adversarial network model, an equipment, a program and a storage medium. In the training method, measurement data of a heterogeneous station is acquired, the measurement data of the heterogeneous station is set as a training sample, and joint training is performed on the heterogeneous generative adversarial network model according to a total objective function. A generator is configured to predict environment data at a future occasion according to environment data of the heterogeneous station at a historical occasion so as to output predicted data. A discriminator is configured to be input the predicted data output by the generator and corresponding measurement data, and discriminate a similarity between the measurement data and the predicted data; a total objective function includes a first objective function of the generator and a second objective function of the discriminator.
-
公开(公告)号：US20230162087A1
公开(公告)日：2023-05-25
申请号：US17989243
申请日：2022-11-17
Inventor： Ji LIU , Chendi ZHOU , Beichen MA , Jiwen ZHOU , Dejing DOU
CPC classification number: G06N20/00 , G06F9/4881
Abstract: A federated learning method, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of distributed data processing and deep learning. The method includes: determining, for each task in a current learning period, a set of target devices corresponding to the task according to respective scheduling information of a plurality of candidate devices corresponding to the task based on a scheduling policy, the scheduling policy enables a time cost information and a device fairness evaluation information of completing the task in the current learning period to meet a predetermined condition; transmitting a global model corresponding to each task to a set of target devices corresponding to the task; and updating the corresponding global model based on trained models in response to receiving the trained models from the corresponding set of target devices.
-
公开(公告)号：US20230080230A1
公开(公告)日：2023-03-16
申请号：US17991977
申请日：2022-11-22
Inventor： Ji LIU , Sunjie YU , Dejing DOU , Jiwen ZHOU
Abstract: A method for generating a federated learning model is provided. The method includes obtaining images; obtaining sorting results of the images; and generating a trained federated learning model by training a federated learning model to be trained according to the images and the sorting results. The federated learning model to be trained is obtained after pruning a federated learning model to be pruned, and a pruning rate of a convolution layer in the federated learning model to be pruned is automatically adjusted according to a model accuracy during the pruning.
-
-
-
-
-
-
-
-
-
Search Results
37
records
(took 0.023 seconds)
