Federated Variational Inference Methods for Structured Latent Variable Models

Conor Hassan, Robert Salomone, Kerrie Mengersen
2/7/2023
stat.MLcs.LGstat.CO

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

86% match1 repo122023

Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework

86% match2025

FedHB: Hierarchical Bayesian Federated Learning

85% match2023

One-Shot Federated Learning with Bayesian Pseudocoresets

83% match2024

Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clustering

83% match2023

Confidence-aware Personalized Federated Learning via Variational Expectation Maximization

83% match1 repo162023

Cite this paper

@article{hassan2023federated,
  title  = {Federated Variational Inference Methods for Structured Latent Variable Models},
  author = {Conor Hassan and Robert Salomone and Kerrie Mengersen},
  year   = {2023},
  eprint = {2302.03314},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.03314v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.03314.svg)](https://codeofpaper.com/paper/2302.03314)

Discussion