fairGNN: Fairness-Aware Gated Neural Networks

Tools for training and analysing fairness-aware gated neural networks for subgroup-aware prediction and interpretation in clinical datasets. Methods draw on prior work in mixture-of-experts neural networks by Jordan and Jacobs (1994) <doi:10.1007/978-1-4471-2097-1_113>, fairness-aware learning by Hardt, Price, and Srebro (2016) <doi:10.48550/arXiv.1610.02413>, and personalised treatment prediction for depression by Iniesta, Stahl, and McGuffin (2016) <doi:10.1016/j.jpsychires.2016.03.016>.

Version:	0.1.0
Depends:	R (≥ 4.1.0)
Imports:	dplyr, tibble, ggplot2, readr, pROC, magrittr, tidyr, purrr, utils, stats, ggalluvial, tidyselect
Suggests:	knitr, torch, testthat, readxl, rmarkdown
Published:	2025-10-26
DOI:	10.32614/CRAN.package.fairGNN (may not be active yet)
Author:	Rhys Holland [aut, cre]
Maintainer:	Rhys Holland <rhys.holland at icloud.com>
BugReports:	https://github.com/rhysholland/fairGNN/issues
License:	MIT + file LICENSE
URL:	https://github.com/rhysholland/fairGNN
NeedsCompilation:	no
SystemRequirements:	Optional 'LibTorch' backend; install via torch::install_torch().
CRAN checks:	fairGNN results

Documentation:

Reference manual:	fairGNN.html , fairGNN.pdf
Vignettes:	Introduction to fairGNN (source, R code)

Downloads:

Package source:	fairGNN_0.1.0.tar.gz
Windows binaries:	r-devel: not available, r-release: not available, r-oldrel: fairGNN_0.1.0.zip
macOS binaries:	r-release (arm64): fairGNN_0.1.0.tgz, r-oldrel (arm64): fairGNN_0.1.0.tgz, r-release (x86_64): fairGNN_0.1.0.tgz, r-oldrel (x86_64): fairGNN_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=fairGNN to link to this page.