This repository is an "Awesome List" curating resources on Federated Learning (FL) and privacy in machine learning. It serves researchers, engineers, and practitioners interested in decentralized AI, offering a comprehensive collection of papers, frameworks, and use cases.

How It Works

The list categorizes resources into key areas: Introduction & Survey, Privacy and Security, System & Application, and Use-cases. It links to seminal papers, recent research, and practical implementations, providing a broad overview of the FL landscape and its challenges, particularly concerning data privacy and system optimization.

Quick Start & Requirements

This is a curated list of resources, not a runnable software project. No installation or specific requirements are needed to browse the content.

Highlighted Details

• Extensive collection of academic papers covering theoretical foundations, privacy mechanisms (e.g., differential privacy, secure aggregation), and system designs for FL.
• Links to prominent open-source FL frameworks like OpenFL, Flower, PySyft, TensorFlow Federated, and FATE.
• Showcases real-world use cases across various domains, including healthcare, mobile computing, and IoT, with contributions from major research institutions and companies.
• Includes benchmarks and datasets specifically designed for FL research, such as LEAF.

Maintenance & Community

The list is maintained by the community, with contributions from various researchers and institutions. Links to related "Awesome Lists" and specific project repositories are provided for deeper engagement.

Licensing & Compatibility

The content itself is a list of links and references, not software. The licensing of linked papers and code repositories varies and must be checked individually.

Limitations & Caveats

As a curated list, it reflects the state of research and development at the time of its last update. Some links may become outdated, and newer advancements in FL might not be immediately incorporated.