BA-BFL: Barycentric Aggregation for Bayesian Federated Learning

• URL: http://arxiv.org/abs/2412.11646v1
• Date: Mon, 16 Dec 2024 10:47:05 GMT
• Title: BA-BFL: Barycentric Aggregation for Bayesian Federated Learning
• Authors: Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou, Marios Kountouris,
• Abstract summary: We study the problem of aggregation in the context of Bayesian Federated Learning (BFL) Using an information geometric perspective, we interpret the BFL aggregation step as finding the barycenter of the trained posteriors for a pre-specified divergence metric. Considering a non-IID setup, we analyze the performance of the developed algorithms against state-of-the-art (SOTA) Bayesian aggregation methods.
• Score: 9.670266892454945
• License:
• Abstract: In this work, we study the problem of aggregation in the context of Bayesian Federated Learning (BFL). Using an information geometric perspective, we interpret the BFL aggregation step as finding the barycenter of the trained posteriors for a pre-specified divergence metric. We study the barycenter problem for the parametric family of $\alpha$-divergences and, focusing on the standard case of independent and Gaussian distributed parameters, we recover the closed-form solution of the reverse Kullback-Leibler barycenter and develop the analytical form of the squared Wasserstein-2 barycenter. Considering a non-IID setup, where clients possess heterogeneous data, we analyze the performance of the developed algorithms against state-of-the-art (SOTA) Bayesian aggregation methods in terms of accuracy, uncertainty quantification (UQ), model calibration (MC), and fairness. Finally, we extend our analysis to the framework of Hybrid Bayesian Deep Learning (HBDL), where we study how the number of Bayesian layers in the architecture impacts the considered performance metrics. Our experimental results show that the proposed methodology presents comparable performance with the SOTA while offering a geometric interpretation of the aggregation phase.

Related papers

• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective. The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning. The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• On Barycenter Computation: Semi-Unbalanced Optimal Transport-based Method on Gaussians [24.473522267391072]
  We develop algorithms on Bures-Wasserstein manifold, named the Exact Geodesic Gradient Descent and Hybrid Gradient Descent algorithms. We establish theoretical convergence guarantees for both methods and demonstrate that the Exact Geodesic Gradient Descent algorithm attains a dimension-free convergence rate.
  arXiv  Detail & Related papers  (2024-10-10T17:01:57Z)
• ScoreFusion: fusing score-based generative models via Kullback-Leibler barycenters [8.08976346461518]
  We introduce ScoreFusion, a theoretically grounded method for fusing multiple pre-trained diffusion models. Our starting point considers the family of KL barycenters of the auxiliary populations, which is proven to be an optimal parametric class in the KL sense. By recasting the learning problem as score matching in denoising diffusion, we obtain a tractable way of computing the optimal KL barycenter weights.
  arXiv  Detail & Related papers  (2024-06-28T03:02:25Z)
• Rethinking Clustered Federated Learning in NOMA Enhanced Wireless Networks [60.09912912343705]
  This study explores the benefits of integrating the novel clustered federated learning (CFL) approach with non-independent and identically distributed (non-IID) datasets. A detailed theoretical analysis of the generalization gap that measures the degree of non-IID in the data distribution is presented. Solutions to address the challenges posed by non-IID conditions are proposed with the analysis of the properties.
  arXiv  Detail & Related papers  (2024-03-05T17:49:09Z)
• FedHB: Hierarchical Bayesian Federated Learning [11.936836827864095]
  We propose a novel hierarchical Bayesian approach to Federated Learning (FL) Our model reasonably describes the generative process of clients' local data via hierarchical Bayesian modeling. We show that our block-coordinate FL algorithm converges to an optimum of the objective at the rate of $O(sqrtt)$.
  arXiv  Detail & Related papers  (2023-05-08T18:21:41Z)
• Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination [23.6031259333814]
  We propose a parallelised (batch) Bayesian quadrature (BQ) method that possesses a provably-exponential convergence rate. We find that our approach significantly outperforms the sampling efficiency of both state-of-the-art BQ techniques and Nested Sampling in various real-world datasets.
  arXiv  Detail & Related papers  (2022-06-09T19:14:52Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)
• Bayesian data-driven discovery of partial differential equations with variable coefficients [9.331440154110117]
  We propose an advanced Bayesian sparse learning algorithm for PDE discovery with variable coefficients. In the experiments, we show that the tBGL-SS method is more robust than the baseline methods under noisy environments.
  arXiv  Detail & Related papers  (2021-02-02T11:05:34Z)
• Model Fusion with Kullback--Leibler Divergence [58.20269014662046]
  We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors.
  arXiv  Detail & Related papers  (2020-07-13T03:27:45Z)
• Disentangled Representation Learning with Wasserstein Total Correlation [90.44329632061076]
  We introduce Wasserstein total correlation in both variational autoencoder and Wasserstein autoencoder settings to learn disentangled latent representations. A critic is adversarially trained along with the main objective to estimate the Wasserstein total correlation term. We show that the proposed approach has comparable performances on disentanglement with smaller sacrifices in reconstruction abilities.
  arXiv  Detail & Related papers  (2019-12-30T05:31:28Z)

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.