arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.06259cs.CVcs.AI
收藏

分段线性神经网络的精确一致解释:一个封闭形式解

Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution

Simon Fraser University(西蒙弗雷泽大学);Huawei Technology Co. Ltd(华为技术有限公司)

Lingyang Chu, Xia Hu, Juhua Hu, Lanjun Wang, Jian Pei

摘要:

由深度神经网络驱动的强大智能机器越来越多地被部署为黑匣子,以在金融和医疗等风险敏感领域做出决策。为了降低潜在风险并与用户建立信任,解释这些机器如何做出决策至关重要。现有的工作通过分析隐藏的神经元,模仿预先训练的模型或近似本地预测来解释预先训练的神经网络。然而,这些方法并不能保证其解释的准确性和一致性。在本文中,我们提出了一个优雅的封闭形式的解决方案,名为$OpenBox$计算精确和一致的解释的家庭分段线性神经网络(PLNN)。其主要思想是首先将PLNN转换为数学上等价的线性分类器集合,然后通过主导其预测的特征来解释每个线性分类器。我们进一步应用$OpenBox$来证明非负和稀疏约束对提高PLNN的可解释性的有效性。在合成和真实世界数据集上的广泛实验清楚地证明了我们解释的准确性和一致性。

英文摘要:

Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical. To reduce potential risk and build trust with users, it is critical to interpret how such machines make their decisions. Existing works interpret a pre-trained neural network by analyzing hidden neurons, mimicking pre-trained models or approximating local predictions. However, these methods do not provide a guarantee on the exactness and consistency of their interpretation. In this paper, we propose an elegant closed form solution named $OpenBox$ to compute exact and consistent interpretations for the family of Piecewise Linear Neural Networks (PLNN). The major idea is to first transform a PLNN into a mathematically equivalent set of linear classifiers, then interpret each linear classifier by the features that dominate its prediction. We further apply $OpenBox$ to demonstrate the effectiveness of non-negative and sparse constraints on improving the interpretability of PLNNs. The extensive experiments on both synthetic and real world data sets clearly demonstrate the exactness and consistency of our interpretation.

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。

↑