Heterogeneous scene-oriented asynchronous federal learning method and device and storage medium

Abstract

The invention discloses a heterogeneous scene-oriented asynchronous federal learning method and device and a storage medium, and the method comprises the steps of determining a target client from candidate clients, the autocorrelation entropy of the target client being higher than the autocorrelation entropy of other clients in the candidate clients; training the target client to obtain a target parameter, and uploading the target parameter to a server; enabling the server to perform aggregation enhancement processing on a model aggregation process according to the target parameter to obtain a first federated model; performing strategy integration processing on the first federated model to obtain a second federated model; and performing model evaluation on the second federated model to determine a target federated model. The invention can improve the model accuracy and reduce the communication cost, and can be widely applied to the technical field of artificial intelligence.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an asynchronous federated learning method, device and storage medium for heterogeneous scenarios. Background technique [0002] With the rapid development of the Internet of Things, a multifunctional network has been created to connect a large number of devices in various fields such as transportation, health care, and administrative management to support diverse data perception and service experience improvement. However, as user information becomes sensitive, the mode of data being collected uniformly in the data center may violate laws and regulations related to data security and privacy protection, making the data processing paradigm begin to shift from centralized data integration to distributed parameter aggregation. [0003] In order to eliminate data islands caused by data security and data privacy, a decentralized mechanism called federated learni...

AI Technical Summary

Problems solved by technology

However, how to integrate client activation, communication optimization, and aggregation enhancement strategies to improve model accuracy while reducing communication costs to effectively support asynchronous federated learning has not been discussed in depth.

Images