FedGVI让联邦学习在模型不准确时仍能可靠预测并量化不确定性。
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
- 基于广义变分推断，支持鲁棒共轭更新，降低客户端计算开销。
- 在合成与真实数据集上均提升预测性能和对模型误设的鲁棒性。
- 适合需要可信不确定度估计的高可靠性场景，如医疗联邦学习。
我们提出 FedGVI，一种稳健的联邦学习概率框架，可应对先验与似然函数建模错误。该方法克服了频率派与贝叶斯联邦学习的局限，在模型误设下仍能提供无偏预测，并实现校准的不确定性量化。相比先前的分区变分推断（Ashman et al., 2022），FedGVI 支持鲁棒且共轭的参数更新，显著降低客户端计算复杂度。理论分析涵盖不动点收敛性、空洞分布最优性及对似然误设的可证明鲁棒性。实证结果表明，该方法在多个合成与真实分类数据集上均提升了鲁棒性与预测表现。
原文摘要 · Abstract (English)
We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentist and Bayesian FL by providing unbiased predictions under model misspecification, with calibrated uncertainty quantification. Our approach generalises previous FL approaches, specifically Partitioned Variational Inference (Ashman et al., 2022), by allowing robust and conjugate updates, decreasing computational complexity at the clients. We offer theoretical analysis in terms of fixed-point convergence, optimality of the cavity distribution, and provable robustness to likelihood misspecification. Further, we empirically demonstrate the effectiveness of FedGVI in terms of improved robustness and predictive performance on multiple synthetic and real world classification data sets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。