mlsanityData to 7 Oct 2026

Federated Variational Inference Methods for Structured Latent Variable Models

arXiv 2302.03314 ↗First posted 7 Feb 2023stat.ML cs.LG stat.COcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

38 of 60 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  8. 2020The Future of Digital Health with Federated Learningcited by 625
  9. 2015Importance Weighted Autoencoderscited by 454
  10. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  11. 2019Monte Carlo Gradient Estimation in Machine Learningcited by 281
  12. 2018Statistical Aspects of Wasserstein Distancescited by 202
26 more
  1. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 187
  2. 2017Autoencoding Variational Inference For Topic Modelscited by 168
  3. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 138
  4. 2017Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inferencecited by 97
  5. 2022Optimal Transport Tools (OTT): A JAX Toolbox for all things Wassersteincited by 96
  6. 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
  7. 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
  8. 2015Scalable Bayes via Barycenter in Wasserstein Spacecited by 44
  9. 2021Challenges and Opportunities in High-dimensional Variational Inferencecited by 35
  10. 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
  11. 2013Asymptotically Exact, Embarrassingly Parallel MCMCcited by 30
  12. 2021QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learningcited by 26
  13. 2017Gaussian variational approximation with a factor covariance structurecited by 22
  14. 2014Structured Stochastic Variational Inferencecited by 21
  15. 2020Automatic structured variational inferencecited by 21
  16. 2016Differentially Private Variational Inference for Non-conjugate Modelscited by 16
  17. 2020Federated Stochastic Gradient Langevin Dynamicscited by 16
  18. 2016Gaussian variational approximation with sparse precision matricescited by 15
  19. 2022Partitioned Variational Inference: A Framework for Probabilistic Federated Learningcited by 13
  20. 2021DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbscited by 11
  21. 2015Parallelizing MCMC with Random Partition Treescited by 10
  22. 2018Gaussian variational approximation for high-dimensional state space modelscited by 10
  23. 2021Implicit copula variational inferencecited by 4
  24. 2022Variational Inference with Locally Enhanced Bounds for Hierarchical Modelscited by 4
  25. 2021Scalable Bayesian inference for time series via divide-and-conquercited by 3
  26. 2021Quasi-Newton Quasi-Monte Carlo for variational Bayescited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2023Federated Variational Inference: Towards Improved Personalization and Generalizationcited by 2
  2. 2025Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Frameworkcited by 1
  3. 2024Federated Learning for Non-factorizable Models using Deep Generative Prior Approximationscited by 0
  4. 2025Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learningcited by 0