PyFed: extending PySyft with N-IID Federated Learning Benchmark
Houda Bouraqqadi, Ayoub Berrag, Mohamed M’Haouach, Afaf Bouhoute, Khalid Fardousse, Ismaïl Berrada · 2021
Federated Learning (FL) is an emerging learning paradigm that enables collaborative model training, across multiple devices using decentralized data, allowing each device to keep the privacy of its local data. Heterogeneity of data distributions is an inherent characteristic of FL. Generally, data samples across user devices are Not-Independent and Identically Distributed (N-IID), making learning in federated settings a challenging task. In this paper, we aim to contribute to FL benchmarking by introducing PyFed, an open source and scalable simulation framework of federated settings, supporting N-IID data. PyFed is fully compatible with PySyft, the secure and private framework for deep learning. It includes a set of benchmark datasets and implements different types of N- IID data distributions. PyFed also provides a set of implementations that can be used as reference for FL development.