Data Mining with Algorithmic Transparency

Data Mining with Algorithmic Transparency
复制标题

具有算法透明性的数据挖掘

DOI:
10.1007/978-3-319-93034-3_11
复制
发表时间:
2018
期刊:
PAKDD 2018: Advances in Knowledge Discovery and Data Mining
影响因子:
--
通讯作者:
Yan Zhou, Yasmeen Alufaisan
Yan Zhou, Yasmeen Alufaisan
中科院分区:
--
文献类型:
--
作者:
Yan Zhou, Yasmeen Alufaisan

文献摘要

参考文献

相似文献

在本文中,我们研究决策树是否可以在不知道学习算法和训练数据的情况下用于解释黑箱分类器。决策树以其透明度和高表达性而闻名。然而,它们也因不稳定和过于庞大的趋势而臭名昭著。我们提出了一个分类器逆向工程模型,该模型输出一个决策树来解释黑盒分类器。有两大挑战。一是建立这样一个稳定性和大小可控的决策树,二是由于安全和经济原因,探测黑箱分类器受到限制。我们的模型通过同时最小化采样成本和分类器复杂性来解决这两个问题。我们在四个真实数据集上给出了我们的经验结果,并证明了我们的逆向工程学习模型可以有效地近似和简化黑箱分类器。
In this paper, we investigate whether decision trees can be used to interpret a black-box classifier without knowing the learning algorithm and the training data. Decision trees are known for their transparency and high expressivity. However, they are also notorious for their instability and tendency to grow excessively large. We present a classifier reverse engineering model that outputs a decision tree to interpret the black-box classifier. There are two major challenges. One is to build such a decision tree with controlled stability and size, and the other is that probing the black-box classifier is limited for security and economic reasons. Our model addresses the two issues by simultaneously minimizing sampling cost and classifier complexity. We present our empirical results on four real datasets, and demonstrate that our reverse engineering learning model can effectively approximate and simplify the black box classifier.
用于分层数据分析的决策树无监督在线学习
DOI: --
发表时间: 1997
期刊: Neural Information Processing Systems
影响因子: --
作者:
Marcus Held;J. Buhmann
通讯作者: J. Buhmann
DOI: 10.1145/2447976.2447990
发表时间: 2013-05-01
影响因子: 22.7
作者:
Sweeney, Latanya
通讯作者: Sweeney, Latanya
DOI: --
发表时间: 2009
期刊: Annual Conference Computational Learning Theory
影响因子: --
作者:
Luis Rademacher;Navin Goyal
通讯作者: Navin Goyal
了解分类器在哪里工作(不工作)——EMM 的 SCaPE 模型类
DOI: --
发表时间: 2014
期刊: 2014 IEEE International Conference on Data Mining
影响因子: --
作者:
W. Duivesteijn;J. Thaele
通讯作者: J. Thaele