FedKT: A Nature-Inspired Bayesian Federated Learning Framework for Privacy-Preserving and Lightweight Consumer Devices
Ying Tian, Hui Chen, Xianxun Zhu, Xiaohan Yu
Abstract
Federated learning (FL) enables collaborative model training across distributed clients without sharing local data, providing an effective paradigm for privacy-preserving learning. To equip FL with principled uncertainty quantification, Bayesian neural networks have been introduced into federated settings. However, existing Bayesian FL frameworks typically rely on dense posterior parameterization or stochastic sampling methods, which lead to high computational and communication overhead and limit their scalability. In this paper, we propose FedKT, a nature-inspired Bayesian federated learning framework that introduces the k-tied parameterization into mean-field variational inference to achieve compact and efficient posterior approximation. By mimicking probabilistic reasoning mechanisms observed in nature, FedKT achieves adaptive and self-regularizing uncertainty modeling across resource-constrained consumer devices. Specifically, by factorizing the variational standard deviations into shared low-rank components, FedKT reduces the parameter complexity from <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i>(<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mn</i>) to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i>(<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i>(<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i>+<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i>)), significantly improving efficiency while maintaining accurate uncertainty estimation. Extensive experiments on four benchmark datasets demonstrate that FedKT achieves comparable or superior predictive accuracy and uncertainty calibration to existing Bayesian FL methods, while ensuring low-energy, privacy-preserving, and scalable training suitable for secure consumer electronic applications.