PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations

PACE：一种用于生成合理且可操作反事实解释的神经符号框架

Abstract: 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.

摘要： 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的预测结果。尽管许多现有方法能够成功生成改变预测结果的替代方案，但由于缺乏将领域知识和干预约束纳入考量的显式机制，它们往往会产生不切实际或不可行的建议。

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.

神经符号人工智能（Neuro-symbolic 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及可行操作的符号推理相结合，提供了一个有前景的研究方向。本文提出了 PACE，这是一个用于生成具备可行性意识（feasibility-aware）反事实解释的模块化神经符号框架。该框架将预测和推理分为两个部分：用于分类的神经预测模型，以及在反事实生成过程中强制执行领域特定约束的符号推理层。

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.

通过对可行性干预进行显式建模，该框架生成的解释既符合领域知识，又保持了可解释性和可操作性。该方法与模型无关，适用于需要现实决策支持的各个领域。

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.

本文在 Adult Income 数据集上进行了案例研究，将多层感知器分类器与答案集编程（ASP）规则相结合，在保留不可变属性的同时，对教育、职业和工作时间的合理修改进行了编码。结果突显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人工智能（XAI）中实现透明且具备可行性意识的反事实解释的潜力。