Fluke: Federated learning utility framework for experimentation and research

Since its inception in 2016, Federated Learning (FL) has gained significant traction in the machine learning community. Several frameworks have been developed to facilitate FL algorithm design, yet researchers often resort to implementing their own solutions from scratch, including simulated environments and baselines. This is likely due to the complexity and inflexibility of existing frameworks, as well as the steep learning curve needed to extend them. In this paper, we introduce fluke , a Python package designed to streamline the development and evaluation of FL algorithms. fluke is specifically tailored for prototyping, making it ideal for researchers and practitioners focused on the learning components of federated systems. fluke is open source and can be used off-the-shelf via its command-line interface or extended with new algorithms with minimal effort. It is designed to be user-friendly, emphasizing ease of use and extensibility. The package includes a wide array of state-of-the-art FL algorithms and datasets, and it is regularly updated to include the latest advancements in the field.