This repository is a curated list of publications on Federated Learning (FL), primarily organized from arXiv. It serves as a comprehensive resource for researchers and practitioners in the FL domain, offering a structured overview of advancements, challenges, and applications.

How It Works

The list categorizes FL research by key areas: Statistical Challenges (data heterogeneity, label deficiency), Trustworthiness (security, privacy, fairness), System Challenges (communication, computation, hardware heterogeneity), Models and Applications (NLP, CV, Healthcare, etc.), and Benchmarks/Surveys. It details publications from top-tier conferences like ICML and NeurIPS, highlighting targeting problems, methods, and contributing institutions.

Quick Start & Requirements

This repository is a curated list and does not require installation or execution. It provides links to research papers and related resources.

Highlighted Details

• Extensive coverage of publications from major ML/CV/NLP/DM conferences (ICML, NeurIPS, CVPR, ACL, AAAI, KDD).
• Categorization of research by statistical, trustworthiness, system, and application challenges.
• Includes a broad range of models and applications, from NLP and Computer Vision to Healthcare and Finance.
• Details specific research areas like Neural Architecture Search, Transfer Learning, and Reinforcement Learning within FL.

Maintenance & Community

The last update mentioned was July 20th, 2021. To contribute or inquire about missing publications, users can email chaoyanghe.com@gmail.com.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific license. The linked publications are subject to their respective licenses and copyright.

Limitations & Caveats

The list's last update was in July 2021, meaning it may not reflect the most recent advancements in Federated Learning. The primary source is stated as arXiv, which may not encompass all FL research.