Skip to content
/ FedGrEM Public

Code for Federated Gradient EM algorithm (FedGrEM) in the ICML paper (Tian et al. 2024)

License

Notifications You must be signed in to change notification settings

ytstat/FedGrEM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

README

This repository provides the code to implement the method FedGrEM and the results in Tian et al. (2024).

The following three code files contain the code implementing algorithm FedGrEM and other benchmark methods considered in the paper as well as evaluating different methods:

  • alignment.R
  • FedGrEM.R
  • estimation_error.R

Please always source these files before calling the functions there.

The following files contain the code for GMM and MoR simulations in the paper:

  • GMM.sh and GMM.R: Gaussian mixture models
  • MoR.sh and MoR.R: Mixture of regression The .sh file is used to call the .R file on the cluster.

Reference

  • Tian, Y., Weng, H., & Feng, Y. (2024, July). Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms. In International Conference on Machine Learning (pp. 48226-48279). PMLR.

About

Code for Federated Gradient EM algorithm (FedGrEM) in the ICML paper (Tian et al. 2024)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published