FairPFN: A Tabular Foundation Model for Causal Fairness

Jake Robertson, Noah Hollmann, Samuel Müller, Noor Awad, Frank Hutter
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51787-51808, 2025.

Abstract

Machine learning (ML) systems are utilized in critical sectors such as healthcare, law enforcement, and finance, but often rely on historical data that contains demographic biases, leading to decisions that perpetuate or intensify existing inequalities. Causal and counterfactual fairness provide a transparent, human-in-the-loop framework to mitigate algorithmic discrimination, aligning closely with legal doctrines of direct and indirect discrimination. However, current causal fairness frameworks hold a key limitation in that they assume prior knowledge of the correct causal model, restricting their applicability in complex fairness scenarios where causal models are unknown or difficult to identify. To bridge this gap, we propose FairPFN, a tabular foundation model pre-trained on synthetic causal fairness data to identify and mitigate the causal effects of protected attributes in its predictions. FairPFN’s key contribution is that it requires no knowledge of the causal model and demonstrates strong performance across a diverse set of hand-crafted and real-world causal scenarios relative to robust baseline methods. FairPFN paves the way for a promising direction for future research, making causal fairness more accessible to a wider variety of complex fairness problems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-robertson25a, title = {{F}air{PFN}: A Tabular Foundation Model for Causal Fairness}, author = {Robertson, Jake and Hollmann, Noah and M\"{u}ller, Samuel and Awad, Noor and Hutter, Frank}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {51787--51808}, 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/robertson25a/robertson25a.pdf}, url = {https://proceedings.mlr.press/v267/robertson25a.html}, abstract = {Machine learning (ML) systems are utilized in critical sectors such as healthcare, law enforcement, and finance, but often rely on historical data that contains demographic biases, leading to decisions that perpetuate or intensify existing inequalities. Causal and counterfactual fairness provide a transparent, human-in-the-loop framework to mitigate algorithmic discrimination, aligning closely with legal doctrines of direct and indirect discrimination. However, current causal fairness frameworks hold a key limitation in that they assume prior knowledge of the correct causal model, restricting their applicability in complex fairness scenarios where causal models are unknown or difficult to identify. To bridge this gap, we propose FairPFN, a tabular foundation model pre-trained on synthetic causal fairness data to identify and mitigate the causal effects of protected attributes in its predictions. FairPFN’s key contribution is that it requires no knowledge of the causal model and demonstrates strong performance across a diverse set of hand-crafted and real-world causal scenarios relative to robust baseline methods. FairPFN paves the way for a promising direction for future research, making causal fairness more accessible to a wider variety of complex fairness problems.} }
Endnote
%0 Conference Paper %T FairPFN: A Tabular Foundation Model for Causal Fairness %A Jake Robertson %A Noah Hollmann %A Samuel Müller %A Noor Awad %A Frank Hutter %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-robertson25a %I PMLR %P 51787--51808 %U https://proceedings.mlr.press/v267/robertson25a.html %V 267 %X Machine learning (ML) systems are utilized in critical sectors such as healthcare, law enforcement, and finance, but often rely on historical data that contains demographic biases, leading to decisions that perpetuate or intensify existing inequalities. Causal and counterfactual fairness provide a transparent, human-in-the-loop framework to mitigate algorithmic discrimination, aligning closely with legal doctrines of direct and indirect discrimination. However, current causal fairness frameworks hold a key limitation in that they assume prior knowledge of the correct causal model, restricting their applicability in complex fairness scenarios where causal models are unknown or difficult to identify. To bridge this gap, we propose FairPFN, a tabular foundation model pre-trained on synthetic causal fairness data to identify and mitigate the causal effects of protected attributes in its predictions. FairPFN’s key contribution is that it requires no knowledge of the causal model and demonstrates strong performance across a diverse set of hand-crafted and real-world causal scenarios relative to robust baseline methods. FairPFN paves the way for a promising direction for future research, making causal fairness more accessible to a wider variety of complex fairness problems.
APA
Robertson, J., Hollmann, N., Müller, S., Awad, N. & Hutter, F.. (2025). FairPFN: A Tabular Foundation Model for Causal Fairness. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:51787-51808 Available from https://proceedings.mlr.press/v267/robertson25a.html.

Related Material