FairPFN: A Tabular Foundation Model for Causal Fairness

2025-06-08

AI Summary

Existing causal fairness methods rely on prior causal graphs, limiting their applicability in complex real-world scenarios where causal structures are unknown. Method: This paper introduces the first tabular foundation model for causal fairness that operates without assuming a predefined causal graph. It leverages synthetic causal data for pretraining to automatically identify and disentangle the causal effects of protected attributes. The approach integrates counterfactual reasoning with causal effect disentanglement training, enabling zero-shot or few-shot cross-domain fair transfer. Contribution/Results: Evaluated on diverse synthetic and real-world datasets, the method reduces average causal bias by 42% over state-of-the-art baselines. It significantly improves generalizability and practicality, marking the first application of the foundation model paradigm to causal fairness.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Computer Vision: Bias, Fairness & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

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.

Problem

• ML systems perpetuate biases from historical data
• Causal fairness requires prior causal model knowledge
• FairPFN mitigates bias without causal model knowledge

Innovation

• Pre-trained on synthetic causal fairness data
• No prior causal model knowledge required
• Identifies and mitigates protected attribute effects