arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.15433cs.AI
收藏

基于模型不可知推理的语义推理

Semantic Reasoning from Model-Agnostic Explanations

Jožef Stefan Institute(约热夫·斯特凡研究所);University of Nova Gorica(新戈里察大学);Jožef Stefan International Postgraduate School(约热夫·斯特凡国际研究生院)

Timen Stepišnik Perdih, Nada Lavrač, Blaž Škrlj

摘要:

随着黑盒模型的广泛采用,基于实例的\emph{post hoc}解释工具(如LIME和SHAP)变得越来越流行。这些工具产生解释,精确定位与给定预测相关的关键特征的贡献。然而,所获得的解释保持在原始特征级别,并且不一定能够被没有广泛领域知识的人类专家理解。我们提出ReEx(推理与解释),一种适用于任意实例级解释器(如SHAP)生成的解释的方法。通过使用本体形式的背景知识,ReEx以最不一般的概括方式概括实例解释。产生的符号描述是特定于单个类的,并根据解释器的输出提供概括。所导出的语义解释潜在地更具有信息性,因为它们在更一般的背景知识的上下文中描述关键属性,例如,在生物过程层面。我们展示了ReEx的表现在9个生物数据集,显示紧凑,语义解释,可以获得更多的信息比通用本体映射,直接链接到功能名称。ReEx是一个简单易用的Python库,与SHAP等工具兼容。据我们所知,这是直接将语义推理与当代模型解释方法相结合的第一种方法之一。这篇文章是预印本。完整版的doi是:10.1109/SAMI50585.2021.9378668

英文摘要:

With the wide adoption of black-box models, instance-based \emph{post hoc} explanation tools, such as LIME and SHAP became increasingly popular. These tools produce explanations, pinpointing contributions of key features associated with a given prediction. However, the obtained explanations remain at the raw feature level and are not necessarily understandable by a human expert without extensive domain knowledge. We propose ReEx (Reasoning with Explanations), a method applicable to explanations generated by arbitrary instance-level explainers, such as SHAP. By using background knowledge in the form of ontologies, ReEx generalizes instance explanations in a least general generalization-like manner. The resulting symbolic descriptions are specific for individual classes and offer generalizations based on the explainer's output. The derived semantic explanations are potentially more informative, as they describe the key attributes in the context of more general background knowledge, e.g., at the biological process level. We showcase ReEx's performance on nine biological data sets, showing that compact, semantic explanations can be obtained and are more informative than generic ontology mappings that link terms directly to feature names. ReEx is offered as a simple-to-use Python library and is compatible with tools such as SHAP and similar. To our knowledge, this is one of the first methods that directly couples semantic reasoning with contemporary model explanation methods. This paper is a preprint. Full version's doi is: 10.1109/SAMI50585.2021.9378668

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。

↑