A Practical Recipe for Federated Learning Under Statistical Heterogeneity Experimental Design

by   Mahdi Morafah, et al.

Federated Learning (FL) has been an area of active research in recent years. There have been numerous studies in FL to make it more successful in the presence of data heterogeneity. However, despite the existence of many publications, the state of progress in the field is unknown. Many of the works use inconsistent experimental settings and there are no comprehensive studies on the effect of FL-specific experimental variables on the results and practical insights for a more comparable and consistent FL experimental setup. Furthermore, the existence of several benchmarks and confounding variables has further complicated the issue of inconsistency and ambiguity. In this work, we present the first comprehensive study on the effect of FL-specific experimental variables in relation to each other and performance results, bringing several insights and recommendations for designing a meaningful and well-incentivized FL experimental setup. We further aid the community by releasing FedZoo-Bench, an open-source library based on PyTorch with pre-implementation of 22 state-of-the-art methods, and a broad set of standardized and customizable features available at https://github.com/MMorafah/FedZoo-Bench. We also provide a comprehensive comparison of several state-of-the-art (SOTA) methods to better understand the current state of the field and existing limitations.


page 1

page 10

page 14


FLGo: A Fully Customizable Federated Learning Platform

Federated learning (FL) has found numerous applications in healthcare, f...

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

Federated learning (FL) is a promising strategy for performing privacy-p...

Heterogeneous Federated Learning: State-of-the-art and Research Challenges

Federated learning (FL) has drawn increasing attention owing to its pote...

FedScale: Benchmarking Model and System Performance of Federated Learning at Scale

We present FedScale, a diverse set of challenging and realistic benchmar...

MrTF: Model Refinery for Transductive Federated Learning

We consider a real-world scenario in which a newly-established pilot pro...

FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization

Hyperparameter optimization (HPO) is crucial for machine learning algori...

pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning

Personalized Federated Learning (pFL), which utilizes and deploys distin...

Please sign up or login with your details

Forgot password? Click here to reset