Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
This addresses the challenge of training deep learning models on distributed, non-IID data without a central server, which is incremental as it builds on existing decentralized learning methods.
The paper tackles the problem of performance degradation in decentralized learning due to heterogeneous data distributions across devices, proposing Global Update Tracking (GUT) which achieves state-of-the-art performance with a 1-6% improvement in test accuracy on various datasets.
Decentralized learning enables the training of deep learning models over large distributed datasets generated at different locations, without the need for a central server. However, in practical scenarios, the data distribution across these devices can be significantly different, leading to a degradation in model performance. In this paper, we focus on designing a decentralized learning algorithm that is less susceptible to variations in data distribution across devices. We propose Global Update Tracking (GUT), a novel tracking-based method that aims to mitigate the impact of heterogeneous data in decentralized learning without introducing any communication overhead. We demonstrate the effectiveness of the proposed technique through an exhaustive set of experiments on various Computer Vision datasets (CIFAR-10, CIFAR-100, Fashion MNIST, and ImageNette), model architectures, and network topologies. Our experiments show that the proposed method achieves state-of-the-art performance for decentralized learning on heterogeneous data via a $1-6\%$ improvement in test accuracy compared to other existing techniques.