This repository is a comprehensive, curated collection of resources on Federated Learning (FL), a machine learning paradigm enabling collaborative model training across decentralized devices without sharing raw data. It targets researchers, engineers, and practitioners in ML, AI, and data mining, offering a structured overview of advancements, tools, and applications.

How It Works

The repository acts as a knowledge hub, meticulously categorizing and linking to research papers, books, code repositories, tutorials, and videos. It organizes information by research directions (e.g., aggregation, personalization, security, efficiency, fairness) and top-tier conference publications (NeurIPS, ICML, ICLR, CVPR, etc.), providing a structured pathway to understand the FL landscape.

Quick Start & Requirements

• Installation: Primarily through git clone for accessing curated lists and links. Specific FL frameworks mentioned (e.g., FedML, Flower, OpenFL) have their own installation procedures, typically via pip or Docker.
• Prerequisites: Python, ML libraries (TensorFlow, PyTorch), and potentially specific hardware for running FL simulations or frameworks.
• Resources: Links to official documentation, demos, and GitHub repositories for various FL frameworks are provided.

Highlighted Details

• Extensive listing of papers from major ML/AI conferences, categorized by research topic and year.
• Curated list of open-source FL frameworks and enterprise-grade platforms.
• Detailed sections on FL attacks (e.g., backdoor, gradient inversion) and defenses (e.g., DP, HE, TEE).
• Coverage of specialized FL areas like personalization, recommender systems, graph neural networks, and incentive mechanisms.

Maintenance & Community

The repository is maintained by innovation-cat and appears to be a community-driven effort, with numerous academic institutions and companies contributing research papers. Links to specific FL framework communities (e.g., Flower) are often available within their respective sections.

Licensing & Compatibility

The repository itself is typically licensed under permissive terms (e.g., MIT License), allowing broad use. However, the linked papers and code repositories are subject to their own licenses, which may vary and could include restrictions on commercial use or derivative works.

Limitations & Caveats

This is a curated list of resources, not a runnable FL framework. The rapid evolution of FL means some links or categorizations might become outdated. Users must consult individual linked resources for specific technical details, dependencies, and licensing.