arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.01792cs.AI
收藏

时间约束下反事实解释的生成

Generating Counterfactual Explanations Under Temporal Constraints

Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);Free University of Bozen-Bolzano(博尔扎诺自由大学);University of Trento(特伦托大学)

Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini, Marco Montali, Massimiliano Ronzani

AI总结:

针对现有反事实解释方法难以适配时序领域、易违反背景知识的问题,提出将LTLp自动机技术融入遗传算法的时序约束反事实生成方法,生成的反事实更具时序合理性与可解释性。

摘要:

反事实解释是可解释人工智能(XAI)领域的重要技术之一,它能提出可改变预测结果的输入数据调整方案,从而带来更优的结果。现有的反事实方法难以直接应用于时序领域,例如流程挖掘场景——这类场景中的数据以活动轨迹的形式存在,必须遵循时序背景知识的约束,该知识明确了哪些动态变化是可行的、哪些是不可行的。具体而言,现成方法生成的反事实可能违反背景知识,导致解释存在矛盾。本研究针对这一挑战,提出了一种生成受时间约束的反事实的新方法,该方法从设计上就能保证符合基于流程轨迹的线性时序逻辑(LTLp)表述的背景知识。我们通过将LTLp的自动机理论技术融入反事实生成的遗传算法中来实现这一目标。实验评估表明,生成的反事实具有时序合理性,在涉及时序依赖的应用中更具可解释性。

英文摘要:

Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods do not readily apply to temporal domains, such as that of process mining, where data take the form of traces of activities that must obey to temporal background knowledge expressing which dynamics are possible and which not. Specifically, counterfactuals generated off-the-shelf may violate the background knowledge, leading to inconsistent explanations. This work tackles this challenge by introducing a novel approach for generating temporally constrained counterfactuals, guaranteed to comply by design with background knowledge expressed in Linear Temporal Logic on process traces (LTLp). We do so by infusing automata-theoretic techniques for LTLp inside a genetic algorithm for counterfactual generation. The empirical evaluation shows that the generated counterfactuals are temporally meaningful and more interpretable for applications involving temporal dependencies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑