System and method of federated learning with diversified feedback
Номер патента: EP4248378A2
Опубликовано: 27-09-2023
Автор(ы): HAN Su, Jialing Wu, Yingxuan Zhu
Принадлежит: Huawei Technologies Co Ltd
Опубликовано: 27-09-2023
Автор(ы): HAN Su, Jialing Wu, Yingxuan Zhu
Принадлежит: Huawei Technologies Co Ltd
Реферат: The present technology discloses a federated learning network including a server and multiple client devices. The server receives a set of parameters of a local machine-learning model from each client device in a subset of the multiple client devices. The set of parameters are combined from each of the client devices in the subset to generate an integrated set of parameters. The server then calculates a parameter difference between the integrated set of parameters and the set of parameters for each client device in the subset. Feedback is sent by the server to each client device in the subset. The feedback is applied during backpropagation of the client. If the local parameters of a client are determined to be invalid for a number of times, the client will be set as an outlier.
Training system and training method of reinforcement learning
Номер патента: US20220215288A1. Автор: Chieh-Lin CHUANG,Chi-Hsuan Lee,Chin-Feng Lai,Yen-I Ouyang,Cheng-Ping TSENG,Wei-Zhong HSU. Владелец: INSTITUTE FOR INFORMATION INDUSTRY. Дата публикации: 2022-07-07.