电子学报2025，Vol.53Issue(6)：1805-1814,10.DOI:10.12263/DZXB.20241166
带特征选择的综合因果多目标反事实解释方法
Comprehensive Causality Multi-Objective Counterfactual Explanation with Feature Selection
摘要
Abstract
The widespread adoption of complex machine learning models across diverse industries has significantly increased the demand for model interpretability.The counterfactual explanation is a crucial post-hoc explanation method.However,traditional approaches often combine multiple objectives into a single objective optimization problem,leading to difficulties in weight assignment and reconciling conflicting objectives.Furthermore,existing methods also suffer from low computational efficiency,degraded prediction accuracy,and insufficient global explanations when dealing with high-dimen-sional,redundant,and noisy data.To address these issues,this article proposes a comprehensive causal multi-objective coun-terfactual explanation method with feature selection(CCE-FS).CCE-FS first employs the maximal information coeffi-cient(MIC)to select key features,thereby enhancing prediction accuracy and global explanatory power.It then formulates the counterfactual search as a multi-objective optimization problem,effectively balancing the relationships between multi-ple objectives.Domain-specific causal relationships are incorporated as constraints to ensure the generated counterfactuals are realistic and plausible.Additionally,CCE-FS provides visual feature effect analysis to enhance user understanding and reveal potential model biases.Experiments conducted on the Statlog dataset demonstrate that CCE-FS significantly im-proves the validity,normality,and sparsity of counterfactual samples through feature selection,achieving a 46.3％enhance-ment in proximity for continuous features.Further validation on the Adult-Income and COMPAS datasets confirms that CCE-FS outperforms existing methods in causal consistency,data distribution reasonableness,and proximity of continuous features.These results highlight CCE-FS's superior explanatory capabilities and greater application potential.关键词
反事实解释/多目标优化/特征选择/因果关系/最大互信息系数/可视化特征效应Key words
counterfactual explanations/multi-objective optimization/feature selection/causal relationship/maxi-mal information coefficient/visualization of feature effects分类
信息技术与安全科学引用本文复制引用
刘金平,汤浩楠,李兴旺,徐鹏飞,袁晟玮..带特征选择的综合因果多目标反事实解释方法[J].电子学报,2025,53(6):1805-1814,10.基金项目
国家自然科学基金(No.62371187) National Natural Science Foundation of China(No.62371187) （No.62371187）
