White-box Induction From SVM Models: Explainable AI with Logic Programming

White-box Induction From SVM Models: Explainable AI with Logic Programming
复制标题

SVM 模型的白盒归纳:通过逻辑编程进行可解释的 AI

DOI:
10.1017/s1471068420000356
复制
发表时间:
2020
影响因子:
1.4
通讯作者:
Gupta, Gopal
Gupta, Gopal
中科院分区:
计算机科学3区
文献类型:
--
作者:
Shakerin, Farhad;Gupta, Gopal

文献摘要

参考文献

被引文献

相似文献

我们专注于问题的诱导逻辑程序,解释模型学习的支持向量机(SVM)算法。自顶向下顺序覆盖归纳逻辑编程(ILP)算法(例如,FOIL)应用爬山搜索,使用信息论的算法。这类算法的一个主要问题是陷入局部最优。然而,在我们的新方法中,数据相关的爬山搜索被模型相关的搜索所取代,其中首先训练全局最优SVM模型,然后算法将支持向量视为模型中最有影响力的数据点,并引入一个子句,该子句将覆盖支持向量和与该支持向量最相似的点。我们的算法没有定义固定的假设搜索空间,而是利用SHAP(可解释AI中的示例特定解释器)来确定相关的特征集。这种方法产生一个算法,捕捉SVM模型的底层逻辑,并优于其他ILP算法的诱导条款和分类评价指标的数量。
We focus on the problem of inducing logic programs that explain models learned by the support vector machine (SVM) algorithm. The top-down sequential covering inductive logic programming (ILP) algorithms (e.g., FOIL) apply hill-climbing search using heuristics from information theory. A major issue with this class of algorithms is getting stuck in local optima. In our new approach, however, the data-dependent hill-climbing search is replaced with a model-dependent search where a globally optimal SVM model is trained first, then the algorithm looks into support vectors as the most influential data points in the model, and induces a clause that would cover the support vector and points that are most similar to that support vector. Instead of defining a fixed hypothesis search space, our algorithm makes use of SHAP, an example-specific interpreter in explainable AI, to determine a relevant set of features. This approach yields an algorithm that captures the SVM model’s underlying logic and outperforms other ILP algorithms in terms of the number of induced clauses and classification evaluation metrics.
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
DOI: 10.1145/1055686.1055687
发表时间: 2005-04
期刊: ACM Trans. Comput. Log.
影响因子: --
作者:
Chiaki Sakama
通讯作者: Chiaki Sakama
使用高效用项集挖掘白盒归纳默认规则
DOI: --
发表时间: 2020
期刊: International Symposium on Practical Aspects of Declarative Languages
影响因子: --
作者:
Farhad Shakerin;G. Gupta
通讯作者: G. Gupta
关于归纳概括的进一步说明
DOI: --
发表时间: 2008
期刊:
影响因子: --
作者:
G. Plotkin
通讯作者: G. Plotkin
DOI: --
发表时间: 2008
期刊: Rule Extraction from Support Vector Machines
影响因子: --
作者:
J. Diederich
通讯作者: J. Diederich