FDGen: A Fairness-Aware Graph Generation Model

Zichong Wang, Wenbin Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65412-65428, 2025.

Abstract

Graph generation models have shown significant potential across various domains. However, despite their success, these models often inherit societal biases, limiting their adoption in real-world applications. Existing research on fairness in graph generation primarily addresses structural bias, overlooking the critical issue of feature bias. To address this gap, we propose FDGen, a novel approach that defines and mitigates both feature and structural biases in graph generation models. Furthermore, we provide a theoretical analysis of how bias sources in graph data contribute to disparities in graph generation tasks. Experimental results on four real-world datasets demonstrate that FDGen outperforms state-of-the-art methods, achieving notable improvements in fairness while maintaining competitive generation performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25ek, title = {{FDG}en: A Fairness-Aware Graph Generation Model}, author = {Wang, Zichong and Zhang, Wenbin}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {65412--65428}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25ek/wang25ek.pdf}, url = {https://proceedings.mlr.press/v267/wang25ek.html}, abstract = {Graph generation models have shown significant potential across various domains. However, despite their success, these models often inherit societal biases, limiting their adoption in real-world applications. Existing research on fairness in graph generation primarily addresses structural bias, overlooking the critical issue of feature bias. To address this gap, we propose FDGen, a novel approach that defines and mitigates both feature and structural biases in graph generation models. Furthermore, we provide a theoretical analysis of how bias sources in graph data contribute to disparities in graph generation tasks. Experimental results on four real-world datasets demonstrate that FDGen outperforms state-of-the-art methods, achieving notable improvements in fairness while maintaining competitive generation performance.} }
Endnote
%0 Conference Paper %T FDGen: A Fairness-Aware Graph Generation Model %A Zichong Wang %A Wenbin Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25ek %I PMLR %P 65412--65428 %U https://proceedings.mlr.press/v267/wang25ek.html %V 267 %X Graph generation models have shown significant potential across various domains. However, despite their success, these models often inherit societal biases, limiting their adoption in real-world applications. Existing research on fairness in graph generation primarily addresses structural bias, overlooking the critical issue of feature bias. To address this gap, we propose FDGen, a novel approach that defines and mitigates both feature and structural biases in graph generation models. Furthermore, we provide a theoretical analysis of how bias sources in graph data contribute to disparities in graph generation tasks. Experimental results on four real-world datasets demonstrate that FDGen outperforms state-of-the-art methods, achieving notable improvements in fairness while maintaining competitive generation performance.
APA
Wang, Z. & Zhang, W.. (2025). FDGen: A Fairness-Aware Graph Generation Model. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:65412-65428 Available from https://proceedings.mlr.press/v267/wang25ek.html.

Related Material