Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME
Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME
复制标题
使用 LIME 归纳非单调逻辑程序来解释提升树模型
DOI：
10.1609/aaai.v33i01.33013052
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
G. Gupta
中科院分区：
文献类型：
--
作者：
Farhad Shakerin;G. Gupta
我们提出了一个启发式算法，诱导非单调逻辑程序，将解释XGBoost训练分类器的行为。我们使用基于LIME方法的技术来局部选择有助于分类决策的最重要的特征。然后，为了解释该模型的全局行为，我们提出了石灰折叠算法-一个基于经验的归纳逻辑编程（ILP）算法能够学习非单调逻辑程序，我们将其应用到由LIME产生的转换数据集。我们提出的方法是不可知的ILP算法的选择。我们的实验与UCI标准基准表明分类评估指标方面的显着改善。同时，与ALEPH（一种最先进的ILP系统）相比，诱导规则的数量显著减少。
We present a heuristic based algorithm to induce nonmonotonic logic programs that will explain the behavior of XGBoost trained classifiers. We use the technique based on the LIME approach to locally select the most important features contributing to the classification decision. Then, in order to explain the model’s global behavior, we propose the LIME-FOLD algorithm —a heuristic-based inductive logic programming (ILP) algorithm capable of learning nonmonotonic logic programs—that we apply to a transformed dataset produced by LIME. Our proposed approach is agnostic to the choice of the ILP algorithm. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics. Meanwhile, the number of induced rules dramatically decreases compared to ALEPH, a state-of-the-art ILP system.
DOI：
10.1007/978-3-662-44923-3
发表时间：
2014-09
期刊：
--
影响因子：
--
作者：
Gerson Zaverucha;V. S. Costa;A. Paes
通讯作者：
Gerson Zaverucha;V. S. Costa;A. Paes