arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.15511cs.LGcs.AI
收藏

BELLATREX:通过LocaLly AccuraTe规则提取器构建解释

BELLATREX: Building Explanations through a LocaLly AccuraTe Rule EXtractor

KU Leuven(鲁汶大学);imec(比利时微电子研究中心)

Klest Dedja, Felipe Kenji Nakano, Konstantinos Pliakos, Celine Vens

摘要:

树集成算法,如随机森林,是一种有效的机器学习方法,因其灵活性、高性能和对过拟合的鲁棒性而流行。然而,由于多个学习器被组合,它们不像单个决策树那样可解释。在这项工作中,我们提出了一种新的方法,即通过LocalLy AccuraTe规则提取器(Bellatrex)建立解释,并且能够解释森林预测对于一个给定的测试实例,只有几个不同的规则。从随机森林生成的决策树开始,我们的方法1)预先选择用于进行预测的规则子集,2)创建此类规则的向量表示,3)将它们投影到低维空间,4)对此类表示进行聚类,以从每个聚类中选择一条规则来解释实例预测。我们在89个真实世界的数据集上测试了Bellatrex的有效性,并证明了我们的方法对于二进制分类,回归,多标签分类和事件时间任务的有效性。据我们所知,这是第一次一个可解释性工具箱可以在同一个框架内处理所有这些任务。我们还表明,我们提取的代理模型可以近似相应的集成模型在所有考虑的任务的性能,而选择只有少数树木从整个森林。我们还表明,我们提出的方法大大优于其他可解释的方法在预测性能。

英文摘要:

Tree-ensemble algorithms, such as random forest, are effective machine learning methods popular for their flexibility, high performance, and robustness to overfitting. However, since multiple learners are combined, they are not as interpretable as a single decision tree. In this work we propose a novel method that is Building Explanations through a LocalLy AccuraTe Rule EXtractor (Bellatrex), and is able to explain the forest prediction for a given test instance with only a few diverse rules. Starting from the decision trees generated by a random forest, our method 1) pre-selects a subset of the rules used to make the prediction, 2) creates a vector representation of such rules, 3) projects them to a low-dimensional space, 4) clusters such representations to pick a rule from each cluster to explain the instance prediction. We test the effectiveness of Bellatrex on 89 real-world datasets and we demonstrate the validity of our method for binary classification, regression, multi-label classification and time-to-event tasks. To the best of our knowledge, it is the first time that an interpretability toolbox can handle all these tasks within the same framework. We also show that our extracted surrogate model can approximate the performance of the corresponding ensemble model in all considered tasks, while selecting only few trees from the whole forest. We also show that our proposed approach substantially outperforms other explainable methods in terms of predictive performance.

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。

↑