Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
From MaRDI portal
Publication:6284034
arXiv1703.02647MaRDI QIDQ6284034
Author name not available (Why is that?)
Publication date: 7 March 2017
Abstract: 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 times faster than the state-of-the-art LIME framework of Ribeiro et al. [2016].
Has companion code repository: https://github.com/eelenberg/streak
This page was built for publication: Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6284034)
