Streaming Weak Submodularity: Interpreting Neural Networks on the Fly

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 eff...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-11
Main Authors: Elenberg, Ethan R, Dimakis, Alexandros G, Feldman, Moran, Karbasi, Amin
Format: Article
Language:English
Subjects:
Algorithms
Classifiers
Combinatorial analysis
Machine learning
Neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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].
ISSN:2331-8422