Wireless federal learning method and device

Abstract

The invention discloses a wireless federated learning method and device, and the method comprises the steps: enabling a distributed learning user based on air computing and a centralized learning user based on non-orthogonal multiple access to share uplink spectrum resources through the concurrent transmission assisted by a dual-function intelligent metasurface, the local data and the model parameters are sent to a base station at the same time for mixed learning; a base station carries out signal decoding on centralized users based on non-orthogonal multiple access so as to obtain local data of each centralized learning user, and the local data are used for calculating model parameters of the centralized learning users; then the base station obtains average model parameters of federated learning users by using serial interference cancellation and air computing technologies; the base station updates a global model by combining the two types of model parameters; and then the base station issues the global model to all federated learning users to carry out the next round of learning until the global model converges or reaches the maximum number of iterations. According to the method, the communication overhead and the transmission delay can be remarkably reduced, and better learning performance can be obtained.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular to a method, device and electronic equipment for wireless federated learning system architecture training. Background technique [0002] With the continuous development of distributed learning technology, federated learning technology enables distributed devices to perform model training collaboratively while processing raw data at the user end. Currently, the problems of communication overhead and latency can be reduced through federated learning based on over-the-air computing. [0003] Dual-function smart metasurface technology is a new type of intelligent reconstruction technology for wireless signal propagation environment. Smart metasurface is a plane composed of a large number of low-cost passive reflective elements, each element can independently induce the amplitude and phase changes of the incident signal , thereby synergistically achieving fine 3D ...

AI Technical Summary

Problems solved by technology

However, in practice, the computing power among local users is diverse, which makes it difficult for devices with insufficient computing power but large amounts of data to collaboratively train shared models.

[0005] Therefore, we urgently need a technology for user heterogeneity to solve the problem of collaborative training caused by insufficient computing power of users.

Images