UGCE: User-Guided Incremental Counterfactual Exploration
This work addresses the need for dynamic and efficient counterfactual explanations in real-world machine learning interpretability, though it is incremental as it builds on existing genetic algorithm methods.
The paper tackles the problem of inefficient counterfactual explanation generation when user constraints evolve over time, proposing UGCE, a genetic algorithm-based framework that incrementally updates counterfactuals, which significantly improves computational efficiency while maintaining high-quality solutions across five benchmark datasets.
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.