Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 53 of its 84 references that are in the map. First posted on arXiv 2 Feb 2025.
Builds on
53 of 84 references.
References · 53
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2016Variational Inference: A Review for Statisticianscited by 1,466
- 2020Adaptive Federated Optimizationcited by 1,036
- 2019Deep Leakage from Gradientscited by 1,004
- 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
- 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
- 2013Expectation Propagation for approximate Bayesian inferencecited by 172
- 2013A General Framework for Updating Belief Distributionscited by 172
- 2015On the properties of variational approximations of Gibbs posteriorscited by 121
- 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
38 more
- 2018An elementary introduction to information geometrycited by 76
- 2021Personalized Federated Learning with Gaussian Processescited by 76
- 2020From Local SGD to Local Fixed-Point Methods for Federated Learningcited by 74
- 2019Variational Federated Multi-Task Learningcited by 69
- 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
- 2021Robust Generalised Bayesian Inference for Intractable Likelihoodscited by 53
- 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
- 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
- 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 34
- 2018Partitioned Variational Inference: A unified framework encompassing federated and continual learningcited by 29
- 2022Gradient Masked Averaging for Federated Learningcited by 22
- 2018Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with β-Divergencescited by 21
- 2020Non-exponentially weighted aggregation: regret bounds for unbounded loss functionscited by 18
- 2015Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Servercited by 17
- 2022A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updatescited by 17
- 2023Federated Learning as Variational Inference: A Scalable Expectation Propagation Approachcited by 17
- 2020Federated Stochastic Gradient Langevin Dynamicscited by 16
- 2023Robust and Scalable Bayesian Online Changepoint Detectioncited by 16
- 2014Expectation propagation as a way of life: A framework for Bayesian inference on partitioned datacited by 14
- 2023Robust and Conjugate Gaussian Process Regressioncited by 14
- 2022Partitioned Variational Inference: A Framework for Probabilistic Federated Learningcited by 13
- 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updatescited by 13
- 2019Embarrassingly parallel MCMC using deep invertible transformationscited by 11
- 2023A numerical approximation method for the Fisher-Rao distance between multivariate normal distributionscited by 11
- 2023Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Spacecited by 10
- 2024The Power of Extrapolation in Federated Learningcited by 10
- 2022Straggler-Resilient Personalized Federated Learningcited by 9
- 2022Deep Leakage from Model in Federated Learningcited by 9
- 2015Combining probability distributions: Extending the logarithmic pooling approachcited by 8
- 2021Adaptation of the Tuning Parameter in General Bayesian Inference with Robust Divergencecited by 7
- 2021Detecting and diagnosing prior and likelihood sensitivity with power-scalingcited by 7
- 2022BOBA: Byzantine-Robust Federated Learning with Label Skewnesscited by 6
- 2014Robust Estimation in Generalised Linear Models : The Density Power Divergence Approachcited by 5
- 2023Bayesian Federated Inference for estimating Statistical Models based on Non-shared Multicenter Data setscited by 5
- 2023Federated Variational Inference Methods for Structured Latent Variable Modelscited by 4
- 2025Connecting Federated ADMM to Bayescited by 4
- 2021Divide-and-Conquer Fusioncited by 3
- 2024Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimizationcited by 3
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.