Awesome-Federated-Machine-Learning

Why we included this project

Anyone getting into federated learning will find this reading list a useful map of the field, whether they are a graduate student, a researcher, or an engineer weighing privacy-preserving training methods. It gathers papers from top machine learning and vision conferences, books, tutorials, videos, and open-source implementations, with the code split into enterprise-grade and research-purpose projects. Papers are grouped by research direction such as model aggregation, personalization, security, fairness, heterogeneity, and client selection, so you can jump straight to the subfield you care about. For teams considering federated learning for real deployments, the curated open-source section is a good place to compare mature frameworks against experimental codebases.