fairGNN-WOD: Fair Graph Learning Without Demographics

This repository contains the models trained as part of a reproduction effort of the paper fairGNN-WOD: Fair Graph Learning Without Demographics by Wang, Liu, Pan, Liu, Saeed, Qiu & Zhang (2025).

For more details see the full repository: https://github.com/adambujna/fairgnn-wod-reproduction/

If you use this repository in your work, please cite the original papers:

Wang, Z., Liu, F., Pan, S., Liu, J., Saeed, F., Qiu, M., & Zhang, W. fairGNN-WOD: Fair Graph Learning Without Demographics. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25 (pp. 556–564).

@inproceedings{ijcai2025p63,
  title     = {fairGNN-WOD: Fair Graph Learning Without Complete Demographics},
  author    = {Wang, Zichong and Liu, Fang and Pan, Shimei and Liu, Jun and Saeed, Fahad and Qiu, Meikang and Zhang, Wenbin},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {556--564},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/63},
  url       = {https://doi.org/10.24963/ijcai.2025/63},
}

Chai, J., Jang, T., & Wang, X. (2022). Fairness without demographics through knowledge distillation. Advances in Neural Information Processing Systems, 35, 19152-19164.

@article{chai2022fairness,
  title={Fairness without demographics through knowledge distillation},
  author={Chai, Junyi and Jang, Taeuk and Wang, Xiaoqian},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={19152--19164},
  year={2022}
}

Kipf, T. N. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.

@article{kipf2016semi,
  title={Semi-supervised classification with graph convolutional networks},
  author={Kipf, TN},
  journal={arXiv preprint arXiv:1609.02907},
  year={2016}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train AdamB2/fact-gnn-wod-ckpts

Paper for AdamB2/fact-gnn-wod-ckpts