# Multi-objective Evolutionary Federated Learning

## TL;DR

This paper introduces a multi-objective evolutionary approach to optimize neural network structures in federated learning, reducing communication costs and improving model accuracy.

## Contribution

It presents a scalable encoding method for neural networks and demonstrates improved performance and efficiency over standard models in federated settings.

## Key findings

- Significant reduction in communication costs.
- Improved global model test errors.
- Effective neural network structure optimization.

## Abstract

Federated learning is an emerging technique used to prevent the leakage of private information. Unlike centralized learning that needs to collect data from users and store them collectively on a cloud server, federated learning makes it possible to learn a global model while the data are distributed on the users' devices. However, compared with the traditional centralized approach, the federated setting consumes considerable communication resources of the clients, which is indispensable for updating global models and prevents this technique from being widely used. In this paper, we aim to optimize the structure of the neural network models in federated learning using a multi-objective evolutionary algorithm to simultaneously minimize the communication costs and the global model test errors. A scalable method for encoding network connectivity is adapted to federated learning to enhance the efficiency in evolving deep neural networks. Experimental results on both multilayer perceptrons and convolutional neural networks indicate that the proposed optimization method is able to find optimized neural network models that can not only significantly reduce communication costs but also improve the learning performance of federated learning compared with the standard fully connected neural networks.