AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributions

2026-09-07

AI Summary

为解决传统方法生成的反事实解释脆弱性问题，提出AVCG框架，通过优化任意假设分布而非单一确定性预测器来生成更鲁棒的反事实解释。

Abstract

Counterfactual explanations formalize"what-if"scenarios by identifying modifications to an input instance that obtain a desired alternative prediction. Traditionally, whether generated via instance-specific optimization or amortized single pass models, these approaches rely on a single, deterministic point-estimate predictor. However, this ignores predictive uncertainty and hypothesis variability, leading to brittle explanations that frequently become invalid if the underlying model is retrained or updated. To address this fragility, we propose the Amortized Variational Counterfactual Generator (AVCG), a generalized optimization framework that formulates counterfactual generation as optimization over an arbitrary distribution of plausible predictive hypotheses rather than a single deterministic predictor. This formulation naturally accommodates Bayesian posteriors, Rashomon-restricted hypothesis spaces, and other uncertainty representations within a unified optimization framework. Evaluation across multiple benchmark datasets demonstrates that the AVCG framework produces counterfactual explanations that remain highly valid under predictive uncertainty and model changes, while maintaining competitive plausibility and single-pass runtime performance.

Problem

• counterfactual explanations
• predictive uncertainty
• hypothesis variability

Innovation

• Amortized Variational Counterfactual Generator
• predictive uncertainty
• hypothesis distribution
• Bayesian posteriors
• Rashomon-restricted hypothesis spaces