PACE: 一种用于合理且可操作的反事实解释的神经符号框架

中文摘要 AI 辅助

反事实解释通过识别能够改变模型决策的最小输入变化来解释机器学习预测。尽管许多现有方法成功生成了改变预测的替代方案，但由于缺乏明确的机制来整合领域知识和干预约束，它们常常产生不现实或不可行的建议。神经符号AI通过将数据驱动的预测模型与能够表示人类可理解规则和可行动作的符号推理相结合，提供了一个有前景的方向。本文提出了PACE，一个模块化的神经符号框架，用于生成考虑可行性的反事实解释。该框架将预测和推理分为两个组件：一个用于分类的神经预测模型和一个符号推理层，在反事实生成过程中强制执行领域特定约束。通过显式建模可行的干预措施，该框架生成的解释与领域知识一致，同时保持可解释性和可操作性。该方法与模型无关，并适用于需要现实决策支持的领域。在Adult Income数据集上进行了一个案例研究，结合了多层感知器分类器和答案集编程（ASP）规则，这些规则编码了对教育、职业和工作时间的可行修改，同时保留了不可变属性。结果突出了反事实有效性与合理性之间的权衡，并表明符号约束产生的解释能更好地满足领域特定的可行性要求，展示了神经符号方法在可解释AI中实现透明、考虑可行性的反事实解释的潜力。

英文摘要

Counterfactual explanations explain machine learning predictions by identifying minimal input changes that would alter a model's decision. Although many existing methods successfully generate prediction-changing alternatives, they often produce unrealistic or infeasible recommendations due to a lack of explicit mechanisms for incorporating domain knowledge and intervention constraints. Neuro-symbolic AI offers a promising direction by combining data-driven predictive models with symbolic reasoning capable of representing human-understandable rules and feasible actions. This paper presents PACE, a modular neuro-symbolic framework for generating feasibility-aware counterfactual explanations. The framework separates prediction and reasoning into two components: a neural predictive model for classification and a symbolic reasoning layer that enforces domain-specific constraints during counterfactual generation. By explicitly modeling feasible interventions, the framework produces explanations consistent with domain knowledge while remaining interpretable and actionable. The approach is model-agnostic and adaptable to domains requiring realistic decision support. A case study is conducted on the Adult Income dataset, combining a multilayer perceptron classifier with Answer Set Programming (ASP) rules encoding feasible modifications to education, occupation, and working hours while preserving immutable attributes. Results highlight the trade-off between counterfactual validity and plausibility and show that symbolic constraints yield explanations that better satisfy domain-specific feasibility requirements, illustrating the potential of neuro-symbolic methods for transparent, feasibility-aware counterfactual explanation in explainable AI.

发表机构

• University of Klagenfurt（克拉根福大学）
• Norwegian University of Life Sciences（挪威生命科学大学）

机构由 AI 辅助整理，请以论文原文为准。