Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness

2024-08-06

AAAI Conference on Artificial Intelligence

AI Summary

Existing counterfactual fairness evaluation methods lack causal interpretability and structured modeling, hindering rigorous individual-level assessment. Method: We propose a sequence-conditioned transport framework integrating causal graphical models with optimal transport theory. Specifically, we extend Knothe–Rearrangement and triangular transport to probabilistic graphical models, enabling causal-constrained, stepwise conditional optimal transport guided by the causal graph structure. This preserves variable dependencies while generating individual-level counterfactuals. Contribution/Results: Our approach yields counterfactuals with enhanced causal plausibility and structural fidelity, as validated on both synthetic and real-world datasets. It establishes a novel, rigorous, traceable, and structure-aware paradigm for individual-level algorithmic fairness evaluation—grounded in causal semantics and geometric transport principles.

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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In this paper, we link two existing approaches to derive counterfactuals: adaptations based on a causal graph, and optimal transport. We extend "Knothe's rearrangement" and "triangular transport" to probabilistic graphical models, and use this counterfactual approach, referred to as sequential transport, to discuss fairness at the individual level. After establishing the theoretical foundations of the proposed method, we demonstrate its application through numerical experiments on both synthetic and real datasets.

Problem

• Link causal graphs and optimal transport for counterfactuals
• Extend triangular transport to probabilistic graphical models
• Apply sequential transport for individual-level fairness analysis

Innovation

• Extends Knothe's rearrangement to probabilistic graphs
• Applies triangular transport for counterfactual fairness
• Uses sequential transport for individual fairness analysis