A study on performance limitations in Federated Learning

TL;DR

This paper investigates the performance limitations of Federated Learning, focusing on communication bottlenecks and data non-IID issues, evaluating their impact on model performance and discussing potential solutions.

Contribution

It provides a detailed analysis of key challenges in federated learning, specifically addressing communication and data heterogeneity issues, with baseline evaluations.

Findings

Communication bottleneck significantly affects model training efficiency.

Data non-IID-ness impacts model accuracy and convergence.

Baseline models reveal the severity of these issues in FL systems.

Abstract

Increasing privacy concerns and unrestricted access to data lead to the development of a novel machine learning paradigm called Federated Learning (FL). FL borrows many of the ideas from distributed machine learning, however, the challenges associated with federated learning makes it an interesting engineering problem since the models are trained on edge devices. It was introduced in 2016 by Google, and since then active research is being carried out in different areas within FL such as federated optimization algorithms, model and update compression, differential privacy, robustness, and attacks, federated GANs and privacy preserved personalization. There are many open challenges in the development of such federated machine learning systems and this project will be focusing on the communication bottleneck and data Non IID-ness, and its effect on the performance of the models. These issues are characterized on a baseline model, model performance is evaluated, and discussions are made to overcome these issues.