{"title":"Local Rule-Based Explanations Method Based on Genetic Algorithms with Fitness Sharing","authors":"Daniel A. Santos, J. A. Baranauskas, Renato Tinós","doi":"10.21528/lnlm-vol21-no2-art1","DOIUrl":null,"url":null,"abstract":"The Local Rule Based Explanations method (LORE) explains decisions of black-box classifiers by using an interpretable model (Decision Tree – DT). The DT is trained with an artificial dataset generated by Genetic Algorithms (GAs). The primary objective of this approach is to replicate the decision boundaries of the black-box model in proximity to the instance under explanation. We show that the artificial examples generated by the GAs in LORE are not necessarily diverse. Consequently, we propose the integration of GAs with fitness sharing in LORE to generate a more diversified subset of artificial examples. The underlying motivation is to ensure that the local decision boundaries of the DT more closely resemble those of the black-box classifier. Experimental results with two classifiers (Multilayer Perceptron and Random Forests), and four classification problems, indicate that LORE with fitness sharing yields more diverse GA populations, consequently leading to improved local explanations. These findings underscore the effectiveness of incorporating fitness sharing into the LORE methodology for enhancing the explainability of black-box classifiers.","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"111 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Learning and Nonlinear Models","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21528/lnlm-vol21-no2-art1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The Local Rule Based Explanations method (LORE) explains decisions of black-box classifiers by using an interpretable model (Decision Tree – DT). The DT is trained with an artificial dataset generated by Genetic Algorithms (GAs). The primary objective of this approach is to replicate the decision boundaries of the black-box model in proximity to the instance under explanation. We show that the artificial examples generated by the GAs in LORE are not necessarily diverse. Consequently, we propose the integration of GAs with fitness sharing in LORE to generate a more diversified subset of artificial examples. The underlying motivation is to ensure that the local decision boundaries of the DT more closely resemble those of the black-box classifier. Experimental results with two classifiers (Multilayer Perceptron and Random Forests), and four classification problems, indicate that LORE with fitness sharing yields more diverse GA populations, consequently leading to improved local explanations. These findings underscore the effectiveness of incorporating fitness sharing into the LORE methodology for enhancing the explainability of black-box classifiers.
基于局部规则的解释方法(LORE)利用一种可解释模型(Decision Tree - DT)来解释黑盒分类器的决策。DT使用遗传算法生成的人工数据集进行训练。这种方法的主要目标是在被解释的实例附近复制黑盒模型的决策边界。我们发现,在LORE中由GAs生成的人工例子并不一定是多样化的。因此,我们提出将ga与LORE中的适应度共享相结合,以生成更多样化的人工示例子集。潜在的动机是确保DT的局部决策边界更接近于黑盒分类器的决策边界。两个分类器(多层感知器和随机森林)和四个分类问题的实验结果表明,具有适应度共享的LORE产生了更多样化的遗传种群,从而改善了局部解释。这些发现强调了将适应度共享纳入LORE方法以增强黑盒分类器的可解释性的有效性。