federa 1.0.0

FedERA is a highly dynamic and customizable framework that can accommodate many use cases with flexibility by implementing several functionalities over different federated learning algorithms, and essentially creating a plug-and-play architecture to accommodate different use cases.

Federated Learning Framework

FedERA is a highly dynamic and customizable framework that can accommodate many use cases with flexibility by implementing several functionalities over different federated learning algorithms, and essentially creating a plug-and-play architecture to accommodate different use cases.

Supported Devices

FedERA has been extensively tested on and works with the following devices:

• Intel CPUs
• Nvidia GPUs
• Nvidia Jetson
• Raspberry Pi
• Intel NUC

With FedERA, it is possible to operate the server and clients on separate devices or on a single device through various means, such as utilizing different terminals or implementing multiprocessing.

Installation

• Install the stable version via PyPi:

$ pip install federa

For more installation options check out the online documentation.

Documentation

Website documentation has been made availbale for FedERA. Please visit FedERA Documentation for more details.

1. Overview
2. Installation
3. Tutorials
4. Contribution
5. API Reference

Federated Learning Algorithms

Following federated learning algorithms are implemented in this framework:

Method	Paper	Publication
FedAvg	Communication-Efficient Learning of Deep Networks from Decentralized Data	AISTATS'2017
FedDyn	Federated Learning Based on Dynamic Regularization	ICLR' 2021
Scaffold	SCAFFOLD: Stochastic Controlled Averaging for Federated Learning	ICML'2020
Personalized FedAvg	Improving Federated Learning Personalization via Model Agnostic Meta Learning	Pre-print
FedAdagrad	Adaptive Federated Optimization	ICML'2020
FedAdam	Adaptive Federated Optimization	ICML'2020
FedYogi	Adaptive Federated Optimization	ICML'2020
Mime	Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning	ICML'2020
Mimelite	Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning	ICML'2020

Datasets Supported

Dataset	Training samples	Test samples	Classes
MNIST	60,000	10,000	10
FashionMnist	60,000	10,000	10
CIFAR-10	50,000	10,000	10
CIFAR-100	50,000	10,000	100

Custom Dataset Support

We also provide a simple way to add your own dataset to the framework. The models employed in this framework were trained using a limited subset of the publicly accessible benchmark dataset MedMNIST v2 (link). We specifically selected four different medical image classes from this dataset, which include breast ultrasound (US), chest X-ray, retinal optical coherence tomography (OCT), and tissue microscopy. Each image within the dataset possesses dimensions of 28x28 pixels. For the framework's implementation, we utilized this custom dataset for both the side server and the client. Look into docs for more details.

Models Supported

FedERA has support for the following Deep Learning models, which are loaded from torchvision.models:

• LeNet-5
• ResNet-18
• ResNet-50
• VGG-16
• AlexNet

Custom Model Support

We also provide a simple way to add your own models to the framework. Look into docs for more details.

Contact

For technical issues related to FedERA development, please contact our development team through Github issues or email ([e-mail]).