FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation


  • Xueyang Wu The Hong Kong University of Science and Technology
  • Hengguan Huang National University of Singapore
  • Youlong Ding Shenzhen University
  • Hao Wang Rutgers University
  • Ye Wang National University of Singapore
  • Qian Xu HKUST




ML: Distributed Machine Learning & Federated Learning, RU: Stochastic Models & Probabilistic Inference


Traditional federated learning (FL) algorithms, such as FedAvg, fail to handle non-i.i.d data because they learn a global model by simply averaging biased local models that are trained on non-i.i.d local data, therefore failing to model the global data distribution. In this paper, we present a novel Bayesian FL algorithm that successfully handles such a non-i.i.d FL setting by enhancing the local training task with an auxiliary task that explicitly estimates the global data distribution. One key challenge in estimating the global data distribution is that the data are partitioned in FL, and therefore the ground-truth global data distribution is inaccessible. To address this challenge, we propose an expectation-propagation-inspired probabilistic neural network, dubbed federated neural propagation (FedNP), which efficiently estimates the global data distribution given non-i.i.d data partitions. Our algorithm is sampling-free and end-to-end differentiable, can be applied with any conventional FL frameworks and learns richer global data representation. Experiments on both image classification tasks with synthetic non-i.i.d image data partitions and real-world non-i.i.d speech recognition tasks demonstrate that our framework effectively alleviates the performance deterioration caused by non-i.i.d data.




How to Cite

Wu, X., Huang, H., Ding, Y., Wang, H., Wang, Y., & Xu, Q. (2023). FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 10399-10407. https://doi.org/10.1609/aaai.v37i9.26237



AAAI Technical Track on Machine Learning IV