Adaptive Federated Learning With Non-IID Data

With the widespread use of Internet of things(IoT) devices, it generates an enormous volume of data, and it is a challenge to mine the IoT data value while ensuring security and privacy. Federated learning is a decentralized approach for training data located on edge devices, such as mobile phones and IoT devices, while keeping privacy, efficiency, and security. However, the Non-IID (non-independent and identically distributed) data, always greatly impacts the performance of the global model. In this paper, we propose a FedDynamic algorithm to solve the statistical challenge of federated learning caused by Non-IID. As Non-IID data can lead to significant differences in model parameters between edge devices, we set different weights for different devices during model aggregation to get a high-performance global model. We analyze and exact key indices (local model accuracy, local data quality, and model difference between local models and the global model), which can reflect the quality of the model, and calculate the aggregation weight for edge devices based on the key indices. Furthermore, we dynamically adjust aggregation weight based on accuracy's variety to solve weight staleness during the training process. Experiments on the MNIST, FMNIST, EMNIST, CINIC-10 and CIFAR-10 datasets show that the FedDynamic algorithm has better accuracy and convergence performance, compared to the FedAvg, FedProx and Scaffold algorithms.

Automated summary

This paper presents a federated learning algorithm called FedDynamic to tackle the statistical challenge caused by non-independent and identically distributed (Non-IID) data. By setting different weights for model aggregation and dynamically adjusting the weights based on key indices, the FedDynamic algorithm achieves better accuracy and convergence performance compared to other existing algorithms.