# Federated Variational Inference: Towards Improved Personalization and Generalization Source: [Federated Variational Inference: Towards Improved Personalization and Generalization]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:21:27.030Z Authors: Elahe Vedadi, Joshua V. Dillon, Philip Andrew Mansfield, Karan Singhal, Arash Afkanpour, Warren Richard Morningstar Published: 2023-05-23T04:28:07.000Z ## Abstract Conventional federated learning algorithms train a single global model by leveraging all participating clients' data. However, due to heterogeneity in client generative distributions and predictive models, these approaches may not appropriately approximate the predictive process, converge to an optimal state, or generalize to new clients. We study personalization and generalization in stateless cross-device federated learning setups assuming heterogeneity in client data distributions and predictive models. We first propose a hierarchical generative model and formalize it using Bayesian Inference. We then approximate this process using Variational Inference to train our model efficiently. We call this algorithm Federated Variational Inference (FedVI). We use PAC-Bayes analysis to provide generalization bounds for FedVI. We evaluate our model on FEMNIST and CIFAR-100 image classification and show that FedVI beats the state-of-the-art on both tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()