Federated learning trains a model on a centralized server using datasets distributed over a large number of edge devices. Applying federated learning ensures data privacy because it does not transfer local data from edge devices to the server. Existing federated learning algorithms assume that all deployed models share the same structure. However, it is often infeasible to distribute the same model to every edge device because of hardware limitations such as computing performance and storage space.

Running neural network models on edge devices is attracting much attention by neural network researchers since edge computing technology is becoming more powerful than ever. However, deploying large neural network models on edge devices is challenging due to the limitation in available computing resources and storage space. Therefore, model compression techniques have been recently studied to reduce the model size and fit models on resource-limited edge devices. Compressing neural network models reduces the size of a model, but also degrades the accuracy of the model since it reduces the precision of weights in the model.

Federated learning is a technique for training machine learning models while keeping data private. The data is kept on the devices or servers where it was collected, and only updates to the model are shared between the parties involved in the training process. This approach is effective in addressing privacy concerns and allows for a diverse dataset, with data coming from multiple sources. However, resource constraints on edge devices make it difficult for all user devices to use the same model, which could impact the model’s accuracy.