UGCE: User-Guided Incremental Counterfactual Exploration

2025-05-27

AI Summary

Existing counterfactual explanation methods lack support for dynamic, time-varying feasibility constraints; each constraint update necessitates full recomputation, resulting in low efficiency and poor adaptability. Method: We propose the first incremental counterfactual exploration framework enabling iterative constraint updates—introducing incremental optimization to counterfactual generation for the first time. Built upon a genetic algorithm, it incorporates a constraint-aware fitness function and a warm-start initialization strategy to enable efficient online adaptation under evolving constraints. Results: Experiments across five benchmark datasets demonstrate that our method achieves significant average speedup over static approaches while preserving solution quality. Moreover, it exhibits strong robustness to diverse, sequentially varying constraint specifications—without compromising interpretability or validity of generated counterfactuals.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Counterfactual explanations (CFEs) are a popular approach for interpreting machine learning predictions by identifying minimal feature changes that alter model outputs. However, in real-world settings, users often refine feasibility constraints over time, requiring counterfactual generation to adapt dynamically. Existing methods fail to support such iterative updates, instead recomputing explanations from scratch with each change, an inefficient and rigid approach. We propose User-Guided Incremental Counterfactual Exploration (UGCE), a genetic algorithm-based framework that incrementally updates counterfactuals in response to evolving user constraints. Experimental results across five benchmark datasets demonstrate that UGCE significantly improves computational efficiency while maintaining high-quality solutions compared to a static, non-incremental approach. Our evaluation further shows that UGCE supports stable performance under varying constraint sequences, benefits from an efficient warm-start strategy, and reveals how different constraint types may affect search behavior.

Problem

• Adapting counterfactual explanations to dynamic user constraints
• Improving efficiency in iterative counterfactual generation
• Maintaining solution quality under evolving feasibility conditions

Innovation

• Genetic algorithm for dynamic counterfactual updates
• User-guided incremental constraint adaptation
• Warm-start strategy boosts efficiency