arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09271cs.LGcs.AI
收藏

寻找树集成模型预测的最小成本解释

Finding Minimum-Cost Explanations for Predictions made by Tree Ensembles

Saab AB(萨布公司);Linköping University(林雪平大学)

John Törnblom, Emil Karlsson, Simin Nadjm-Tehrani

AI总结:

本文提出高效预言机和m-MARCO算法,为树集成模型预测寻找成本最小化的解释,在保证正确性的同时大幅提升计算速度,并证明最小解释比大量最小解释更简洁。

摘要:

当机器学习模型被人类操作员用作关键系统的决策支持时,解释其为何得出特定预测的能力至关重要。所提供的解释必须是可证明正确的,并且最好没有冗余信息,这被称为最小解释。在本文中,我们旨在为树集成模型做出的预测寻找不仅是最小的,而且是在成本函数方面达到最小化的解释。为此,我们首先提出了一个高效的预言机,它能够判定解释的正确性,在计算最小解释时,其运行时性能比当前最先进的替代方案高出几个数量级。其次,我们从相关工作中改编了一种名为MARCO的算法(称之为m-MARCO),用于为每个预测计算单个最小解释,并展示了与枚举所有最小解释的MARCO算法相比,整体加速因子为二。最后,我们研究了一系列用例中获得的解释,从而对其特征有了进一步的见解。特别是,我们观察到在若干情况下,单个预测有超过100,000种最小解释可供选择。在这些情况下,我们看到只有一小部分最小解释同时也是最小化的,并且最小解释的冗长程度显著降低,从而激发了本工作的目标。

英文摘要:

The ability to explain why a machine learning model arrives at a particular prediction is crucial when used as decision support by human operators of critical systems. The provided explanations must be provably correct, and preferably without redundant information, called minimal explanations. In this paper, we aim at finding explanations for predictions made by tree ensembles that are not only minimal, but also minimum with respect to a cost function. To this end, we first present a highly efficient oracle that can determine the correctness of explanations, surpassing the runtime performance of current state-of-the-art alternatives by several orders of magnitude when computing minimal explanations. Secondly, we adapt an algorithm called MARCO from related works (calling it m-MARCO) for the purpose of computing a single minimum explanation per prediction, and demonstrate an overall speedup factor of two compared to the MARCO algorithm which enumerates all minimal explanations. Finally, we study the obtained explanations from a range of use cases, leading to further insights of their characteristics. In particular, we observe that in several cases, there are more than 100,000 minimal explanations to choose from for a single prediction. In these cases, we see that only a small portion of the minimal explanations are also minimum, and that the minimum explanations are significantly less verbose, hence motivating the aim of this work.

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。

↑