FairPFN: A Tabular Foundation Model for Causal Fairness

TL;DR

FairPFN is a novel tabular foundation model that pre-trains on synthetic data to identify and mitigate causal effects of protected attributes without requiring prior causal knowledge, enhancing fairness in ML systems.

Contribution

It introduces a causal fairness foundation model that operates without prior causal model knowledge, broadening applicability in complex fairness scenarios.

Findings

Strong performance in identifying protected causal effects

Effective across diverse real-world scenarios

Outperforms baseline methods in fairness tasks

Abstract

Machine learning (ML) systems are utilized in critical sectors, such as healthcare, law enforcement, and finance. However, these systems are often trained on historical data that contains demographic biases, leading to ML decisions that perpetuate or exacerbate existing social inequalities. Causal fairness provides 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 still demonstrates strong performance in identifying and removing protected causal effects across a diverse set of hand-crafted and real-world scenarios relative to robust baseline methods. FairPFN paves the way for promising future research, making causal fairness more accessible to a wider variety of complex fairness problems.