Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
复制标题
DOI：
--
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Ethan R. Elenberg;A. Dimakis;Moran Feldman;Amin Karbasi
中科院分区：
文献类型：
--
作者：
Ethan R. Elenberg;A. Dimakis;Moran Feldman;Amin Karbasi
在许多机器学习应用程序中，重要的是要解释黑盒分类器的预测。例如，为什么深度神经网络将图像分配给特定类别？我们将黑盒分类器作为组合最大化问题的解释性提出了可解释性，并提出了一种有效的流算法来解决其受基质性约束的依据。通过扩展Badanidiyuru等人的想法。 [2014]，在随机流顺序和弱的子模化目标函数的情况下，我们为我们的算法提供了恒定的因子近似保证。这是该通用类功能类别的第一个这样的理论保证，我们还表明，对于最坏的情况流顺序不存在这种算法。我们的算法获得了Inception V3预测的类似解释，比Ribeiro等人的最先进的石灰框架快$ 10 $倍。 [2016]。
In many machine learning applications, it is important to explain the predictions of a black-box classifier. For example, why does a deep neural network assign an image to a particular class? We cast interpretability of black-box classifiers as a combinatorial maximization problem and propose an efficient streaming algorithm to solve it subject to cardinality constraints. By extending ideas from Badanidiyuru et al. [2014], we provide a constant factor approximation guarantee for our algorithm in the case of random stream order and a weakly submodular objective function. This is the first such theoretical guarantee for this general class of functions, and we also show that no such algorithm exists for a worst case stream order. Our algorithm obtains similar explanations of Inception V3 predictions $10$ times faster than the state-of-the-art LIME framework of Ribeiro et al. [2016].