FairPFN: Transformers Can do Counterfactual Fairness

TL;DR

FairPFN introduces a transformer-based model pretrained on synthetic data to achieve counterfactual fairness in machine learning, reducing reliance on causal models and domain knowledge, with promising results on synthetic and real datasets.

Contribution

This work presents the first transformer model, FairPFN, for counterfactual fairness that learns to eliminate causal effects of protected attributes without needing explicit causal models.

Findings

Effective in removing causal impact of protected attributes

Works well on synthetic and real-world datasets

Paves new research directions in fairness with transformers

Abstract

Machine Learning systems are increasingly prevalent across healthcare, law enforcement, and finance but often operate on historical data, which may carry biases against certain demographic groups. Causal and counterfactual fairness provides an intuitive way to define fairness that closely aligns with legal standards. Despite its theoretical benefits, counterfactual fairness comes with several practical limitations, largely related to the reliance on domain knowledge and approximate causal discovery techniques in constructing a causal model. In this study, we take a fresh perspective on counterfactually fair prediction, building upon recent work in in context learning (ICL) and prior fitted networks (PFNs) to learn a transformer called FairPFN. This model is pretrained using synthetic fairness data to eliminate the causal effects of protected attributes directly from observational data, removing the requirement of access to the correct causal model in practice. In our experiments, we thoroughly assess the effectiveness of FairPFN in eliminating the causal impact of protected attributes on a series of synthetic case studies and real world datasets. Our findings pave the way for a new and promising research area: transformers for causal and counterfactual fairness.