Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation

• URL: http://arxiv.org/abs/2505.14161v1
• Date: Tue, 20 May 2025 10:14:32 GMT
• Title: Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
• Authors: Ting Wei, Biao Mei, Junliang Lyu, Renquan Zhang, Feng Zhou, Yifan Sun,
• Abstract summary: FedWBA is a novel PBFL method that enhances both local inference and global aggregation.<n>We provide local and global convergence guarantees for FedWBA.<n>Experiments show that FedWBA outperforms baselines in prediction accuracy, uncertainty calibration, and convergence rate.
• Score: 7.3170276716290354
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Personalized Bayesian federated learning (PBFL) handles non-i.i.d. client data and quantifies uncertainty by combining personalization with Bayesian inference. However, existing PBFL methods face two limitations: restrictive parametric assumptions in client posterior inference and naive parameter averaging for server aggregation. To overcome these issues, we propose FedWBA, a novel PBFL method that enhances both local inference and global aggregation. At the client level, we use particle-based variational inference for nonparametric posterior representation. At the server level, we introduce particle-based Wasserstein barycenter aggregation, offering a more geometrically meaningful approach. Theoretically, we provide local and global convergence guarantees for FedWBA. Locally, we prove a KL divergence decrease lower bound per iteration for variational inference convergence. Globally, we show that the Wasserstein barycenter converges to the true parameter as the client data size increases. Empirically, experiments show that FedWBA outperforms baselines in prediction accuracy, uncertainty calibration, and convergence rate, with ablation studies confirming its robustness.

Related papers

• Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning [1.3270838622986498]
  Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local.<n>Traditional FL approaches rely on a centralized, star-shaped topology, where a central server aggregates model updates from clients.<n>We propose a decentralized, peer-to-peer (P2P) FL framework to enable each client to identify and aggregate a personalized set of trustworthy and beneficial updates.
  arXiv  Detail & Related papers  (2025-08-07T10:10:37Z)
• Information-Geometric Barycenters for Bayesian Federated Learning [9.670266892454945]
  Federated learning (FL) is used to achieve consensus through averaging locally trained models.<n>While effective, this approach may not align well with Bayesian inference, where the model space has the structure of a distribution space.<n>We propose BA-FLB, an algorithm that retains convergence properties of Federated Averaging in nonindependent settings.
  arXiv  Detail & Related papers  (2024-12-16T10:47:05Z)
• Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space [27.259110269667826]
  Federated Learning (FL) involves training a model over a dataset distributed among clients. Small and noisy datasets are common, highlighting the need for well-calibrated models. We propose $beta$-Predictive Bayes, a Bayesian FL algorithm that interpolates between a mixture and product of the predictive posteriors.
  arXiv  Detail & Related papers  (2023-12-15T14:17:16Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clustering [6.829317124629158]
  Federated learning (FL) is a promising framework that models distributed machine learning. FL suffers performance degradation from heterogeneous and limited data. We present a novel personalized Bayesian FL approach named pFedBayes and a clustered FL model named cFedbayes.
  arXiv  Detail & Related papers  (2023-03-08T02:52:40Z)
• $\ exttt{FedBC}$: Calibrating Global and Local Models via Federated Learning Beyond Consensus [66.62731854746856]
  In federated learning (FL), the objective of collaboratively learning a global model through aggregation of model updates across devices tends to oppose the goal of personalization via local information. In this work, we calibrate this tradeoff in a quantitative manner through a multi-criterion-based optimization. We demonstrate that $texttFedBC$ balances the global and local model test accuracy metrics across a suite datasets.
  arXiv  Detail & Related papers  (2022-06-22T02:42:04Z)
• DELTA: Diverse Client Sampling for Fasting Federated Learning [9.45219058010201]
  Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently. Existing sampling methods are either biased or can be further optimized for faster convergence. We present DELTA, an unbiased sampling scheme designed to alleviate these issues.
  arXiv  Detail & Related papers  (2022-05-27T12:08:23Z)
• On The Impact of Client Sampling on Federated Learning Convergence [4.530678016396477]
  We introduce a novel decomposition theorem for the convergence of FL, allowing to clearly quantify the impact of client sampling on the global model update. Our results suggest that MD sampling should be used as default sampling scheme, due to the resilience to the changes in data ratio during the learning process, while Uniform sampling is superior only in the special case when clients have the same amount of data.
  arXiv  Detail & Related papers  (2021-07-26T13:36:06Z)
• Federated Functional Gradient Boosting [75.06942944563572]
  We study functional minimization in Federated Learning. For both FFGB.C and FFGB.L, the radii of convergence shrink to zero as the feature distributions become more homogeneous.
  arXiv  Detail & Related papers  (2021-03-11T21:49:19Z)
• A Bayesian Federated Learning Framework with Online Laplace Approximation [144.7345013348257]
  Federated learning allows multiple clients to collaboratively learn a globally shared model. We propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. We achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
  arXiv  Detail & Related papers  (2021-02-03T08:36:58Z)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.