FnRGNN is a fairness-aware framework for graph neural network–based node regression. By combining edge reweighting, representation alignment, and prediction normalization, it mitigates bias in continuous regression tasks while preserving model performance.

This codebase utilizes Anaconda for managing environmental dependencies. Please follow these steps to set up the environment:

1. Download Anaconda: Click here to download Anaconda.
2. Clone the Repository: Clone the repository using the following command.

   git clone https://github.com/sybeam27/FnRGNN.git

3. Install Requirements:
   • Navigate to the cloned repository:

     cd FnRGNN

   • Create a Conda environment from the provided env.yml file:

     conda env create -f env.yml

   • Activate the Conda environment:

     conda activate fair-gnn

This will set up the environment required to run the codebase.

Below are the github links for datasets used in our experiments:

All datasets should be stored in the datasets folder, with each dataset placed in a subfolder named after the dataset (e.g., datasets/NBA/, datasets/NIFTY/, etc.).

1. Pokec (GitHub)
2. NBA (GitHub)
3. German (GitHub)

We extend our gratitude to the authors of the following libraries for generously sharing their source code and dataset: FairGNN, FMP, NIFTY.

Your contributions are greatly appreciated.

CIKM 2025