Awesome-Federated-Learning

Why we included this project

Federated learning has a steep reading curve, and this list is a good way to climb it. The author took papers from arXiv and reorganized them into tables grouped by venue, targeting problem, and method, so you can compare how different approaches handle non-IID data, communication cost, and privacy without wading through raw paper listings. It also points to the FedML library and the 'Advances and Open Problems in Federated Learning' survey, giving newcomers a route from background reading into actual tooling. Since the FedML team maintains the list and has folded it into their research documentation, it stays reasonably current and works well as a first stop before digging into primary sources.