Federated learning lower edge end collaborative channel adaptability gradient compression method

Abstract

The invention discloses a federated learning lower edge collaborative channel adaptability gradient compression method. The method comprises the following steps: S1, each terminal sends a known training sequence to an edge server by using an uplink channel; s2, the edge server estimates the uplink channel condition of each terminal according to the degradation degree of the training sequence sent by each terminal after passing through the channel, and stores the channel gain parameter of each uplink channel; s3, the edge server solves an optimization problem by using the channel condition of the terminal and the set total quantization bit number, and performs quantization bit number distribution; s4, the edge server broadcasts quantized bit number information which can be used by each terminal to the terminals participating in federated learning; and S5, the terminal finds a quantization bit number which can be used by the terminal in the broadcast information, and quantizes the local update gradient. The method has the advantages that the influence of wireless communication channel degradation on the federated learning training effect is effectively relieved, the communication bottleneck is relieved, and the anti-noise performance of the system is improved.

Description

technical field [0001] The invention belongs to the technical field of federated learning gradient compression, and in particular relates to a channel adaptive gradient compression method under federated learning with side-end cooperation. Background technique [0002] With the rise of mobile smart devices, a large amount of data is scattered at the edge, limited communication resources and user privacy protection make the distributed machine learning framework - federated learning develop rapidly. In the federated learning framework, the terminal uses local data for local model training, uploads the trained local model parameters to the edge server, and the edge server aggregates all local model parameters to update the global model parameters, and then broadcasts the global model parameters, and the entire federated learning is carried out. The above steps are iterated until the global model converges. However, due to the increasing complexity of user data, the parameter ...

AI Technical Summary

Problems solved by technology

[0004] 1. The terminal cluster is usually located within the service range of the same edge server, and its uplink channel can be regarded as multiple independent and orthogonal sub-channels divided by the total uplink channel, and the total channel capacity is limited

[0005] 2. The uplink channel of the terminal has channel fading and channel noise that are common in wireless communication channels. When the quantized stochastic gradient is transmitted through this type of fading channel, the data will be damaged to a certain extent.

When the edge server uses lossy stochastic gradients for aggregation and global iteration, the resulting global model will deviate from the ideal global model, making federated learning performance worse

Images