Democratizing AI in Africa: FL for Low-Resource Edge Devices

TL;DR

This paper demonstrates how federated learning can enable low-resource edge devices in Africa to collaboratively train AI models for healthcare, improving generalizability despite limited computational resources.

Contribution

It introduces a federated learning approach tailored for low-resource devices in Africa, enhancing AI accessibility and model robustness in healthcare applications.

Findings

Federated learning outperforms local models in generalizability.

Model performance is comparable between centralized and federated approaches.

Low-resource devices like Raspberry Pi can effectively participate in federated training.

Abstract

Africa faces significant challenges in healthcare delivery due to limited infrastructure and access to advanced medical technologies. This study explores the use of federated learning to overcome these barriers, focusing on perinatal health. We trained a fetal plane classifier using perinatal data from five African countries: Algeria, Ghana, Egypt, Malawi, and Uganda, along with data from Spanish hospitals. To incorporate the lack of computational resources in the analysis, we considered a heterogeneous set of devices, including a Raspberry Pi and several laptops, for model training. We demonstrate comparative performance between a centralized and a federated model, despite the compute limitations, and a significant improvement in model generalizability when compared to models trained only locally. These results show the potential for a future implementation at a large scale of a federated learning platform to bridge the accessibility gap and improve model generalizability with very little requirements.