融合反事实与特征重要性，提升神经网络解释的可行性与多样性
GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
- 结合反事实生成与特征归因，优化解释的可行性、合理性和多样性
- 在多分类场景下表现优于现有方法，生成更贴近真实的数据扰动
- 适合医疗、金融等高风险领域，帮助理解模型决策依据
可解释人工智能（XAI）在医疗、金融等关键领域日益重要，为AI决策提供透明性。当前两大解释范式——反事实解释（CFX）和特征归因（FA）——各有侧重。本文提出GradCFA，一种融合CFX与FA的混合框架，通过显式优化可行性、合理性与多样性，弥补现有方法的不平衡问题。不同于多数仅针对二分类的研究，GradCFA拓展至多分类场景，适用范围更广。我们在多个基准上评估了其有效性、接近度、稀疏性、合理性与多样性，对比了Wachter、DiCE、CARE（CFX）和SHAP（FA）等先进方法。结果表明，GradCFA能生成可行、合理且多样化的反事实样本，并提供有价值的特征重要性分析，有效揭示关键影响因素及其作用。代码已开源：https://github.com/jacob-ws/GradCFs。
原文摘要 · Abstract (English)
Explainable Artificial Intelligence (XAI) is increasingly essential as AI systems are deployed in critical fields such as healthcare and finance, offering transparency into AI-driven decisions. Two major XAI paradigms, counterfactual explanations (CFX) and feature attribution (FA), serve distinct roles in model interpretability. This study introduces GradCFA, a hybrid framework combining CFX and FA to improve interpretability by explicitly optimizing feasibility, plausibility, and diversity - key qualities often unbalanced in existing methods. Unlike most CFX research focused on binary classification, GradCFA extends to multi-class scenarios, supporting a wider range of applications. We evaluate GradCFA's validity, proximity, sparsity, plausibility, and diversity against state-of-the-art methods, including Wachter, DiCE, CARE for CFX, and SHAP for FA. Results show GradCFA effectively generates feasible, plausible, and diverse counterfactuals while offering valuable FA insights. By identifying influential features and validating their impact, GradCFA advances AI interpretability. The code for implementation of this work can be found at: https://github.com/jacob-ws/GradCFs .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。