Federated learning methods enable model training across distributed data sources without data leaving their original locations and have gained increasing interest in various fields. However, existing approaches are limited, excluding many structured probabilistic models. We present a general and elegant solution based on structured variational inference, widely used in Bayesian machine learning, adapted for the federated setting. Additionally, we provide a communication-efficient variant analogous to the canonical FedAvg algorithm. The proposed algorithms' effectiveness is demonstrated, and their performance is compared with hierarchical Bayesian neural networks and topic models.

翻译：联邦学习方法使分布式数据源在不离开原始位置的情况下进行模型训练，并在各个领域日益引起关注。然而，现有方法存在局限性，排除了许多结构化概率模型。我们提出了一种基于结构化变分推断的通用且优雅的解决方案，该方法在贝叶斯机器学习中广泛应用，并针对联邦场景进行了适配。此外，我们提供了一种类似于经典FedAvg算法的通信高效变体。我们展示了所提出算法的有效性，并将其性能与分层贝叶斯神经网络和主题模型进行了对比。