US Patent Application 18336895. System and Method of Federated Learning with Diversified Feedback simplified abstract

From WikiPatents
Jump to navigation Jump to search

System and Method of Federated Learning with Diversified Feedback

Organization Name

Huawei Technologies Co., Ltd.==Inventor(s)==

[[Category:Yingxuan Zhu of Plano TX (US)]]

[[Category:Jialing Wu of Plano TX (US)]]

[[Category:Han Su of Plano TX (US)]]

System and Method of Federated Learning with Diversified Feedback - A simplified explanation of the abstract

This abstract first appeared for US patent application 18336895 titled 'System and Method of Federated Learning with Diversified Feedback

Simplified Explanation

The patent application describes a federated learning network that includes a server and multiple client devices.

  • The server receives parameters of a local machine-learning model from each client device in a subset of the multiple client devices.
  • The server combines the parameters from each client device in the subset to generate an integrated set of parameters.
  • The server calculates the difference between the integrated set of parameters and the set of parameters for each client device in the subset.
  • The server provides feedback to each client device in the subset, which 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 is set as an outlier.


Original Abstract Submitted

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.

Retrieved from "http://wikipatents.org/index.php?title=US_Patent_Application_18336895._System_and_Method_of_Federated_Learning_with_Diversified_Feedback_simplified_abstract&oldid=9588"