mlsanityData to 14 Oct 2026

Partitioned Variational Inference: A Framework for Probabilistic Federated Learning

arXiv 2202.12275 ↗First posted 24 Feb 2022stat.ML cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

The proliferation of computing devices has brought about an opportunity to deploy machine learning models on new problem domains using previously inaccessible data. Traditional algorithms for training such models often require data to be stored on a single machine with compute performed by a single node, making them unsuitable for decentralised training on multiple devices. This deficiency has motivated the development of federated learning algorithms, which allow multiple data owners to train collaboratively and use a shared model whilst keeping local data private. However, many of these algorithms focus on obtaining point estimates of model parameters, rather than probabilistic estimates capable of capturing model uncertainty, which is essential in many applications. Variational inference (VI) has become the method of choice for fitting many modern probabilistic models. In this paper we introduce partitioned variational inference (PVI), a general framework for performing VI in the federated setting. We develop new supporting theory for PVI, demonstrating a number of properties that make it an attractive choice for practitioners; use PVI to unify a wealth of fragmented, yet related literature; and provide empirical results that showcase the effectiveness of PVI in a variety of federated settings.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 26 of its 68 references that are in the map. First posted on arXiv 24 Feb 2022.

Builds on

26 of 68 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2015Variational Inference with Normalizing Flowscited by 2,170
  4. 2013Gaussian Processes for Big Datacited by 383
  5. 2017Variational Continual Learningcited by 339
  6. 2017Multitask learning and benchmarking with clinical time series datacited by 290
  7. 2017Advances in Variational Inferencecited by 236
  8. 2013Expectation Propagation for approximate Bayesian inferencecited by 174
  9. 2016Automatic Differentiation Variational Inferencecited by 159
  10. 2017Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Modelscited by 65
  11. 2020Generalized Variational Continual Learningcited by 56
  12. 2013The Information Geometry of Mirror Descentcited by 54
14 more
  1. 2013Streaming Variational Bayescited by 48
  2. 2017Streaming Sparse Gaussian Process Approximationscited by 41
  3. 2018Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Modelscited by 38
  4. 2018Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Modelscited by 38
  5. 2017Deep Probabilistic Programmingcited by 24
  6. 2015Stochastic Expectation Propagationcited by 22
  7. 2018Overpruning in Variational Bayesian Neural Networkscited by 22
  8. 2015Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functionscited by 19
  9. 2015Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Servercited by 17
  10. 2016Differentially Private Variational Inference for Non-conjugate Modelscited by 16
  11. 2019Improving and Understanding Variational Continual Learningcited by 12
  12. 2015A trust-region method for stochastic variational inference with applications to streaming datacited by 9
  13. 2019Differentially Private Federated Variational Inferencecited by 3
  14. 2015Incremental Variational Inference for Latent Dirichlet Allocationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 6; 2026: 1.

13 papers.

Sort:

  1. 2023Federated Learning as Variational Inference: A Scalable Expectation Propagation Approachcited by 17
  2. 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
  3. 2025Knowledge Adaptation as Posterior Correctioncited by 6
  4. 2023Federated Variational Inference Methods for Structured Latent Variable Modelscited by 4
  5. 2025Connecting Federated ADMM to Bayescited by 4
  6. 2025Federated ADMM from Bayesian Dualitycited by 3
  7. 2022Differentially private partitioned variational inferencecited by 2
  8. 2024One-Shot Federated Learning with Bayesian Pseudocoresetscited by 1
  9. 2025Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Frameworkcited by 1
  10. 2024Compressed Bayesian Federated Learning for Reliable Passive Radio Sensing in Industrial IoTcited by 0
  11. 2025Bayesian Federated Learning for Continual Trainingcited by 0
  12. 2025Decentralized Federated Learning of Probabilistic Generative Classifierscited by 0
1 more
  1. 2026Gaussian Mean Field Variational Inference can Overestimate Predictive Variancecited by 0