Streaming Weak Submodularity: Interpreting Neural Networks on the Fly

03/08/2017
by   Ethan R. Elenberg, et al.
0

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].

READ FULL TEXT

page 9

page 11

page 17

page 18

research
07/21/2018

Streaming Methods for Restricted Strongly Convex Functions with Applications to Prototype Selection

In this paper, we show that if the optimization function is restricted-s...
research
06/15/2017

Robust Submodular Maximization: A Non-Uniform Partitioning Approach

We study the problem of maximizing a monotone submodular function subjec...
research
07/13/2017

Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?

Submodular functions are a broad class of set functions, which naturally...
research
11/17/2017

Multi-Objective Maximization of Monotone Submodular Functions with Cardinality Constraint

We consider the problem of multi-objective maximization of monotone subm...
research
06/01/2016

Stream Clipper: Scalable Submodular Maximization on Stream

Applying submodular maximization in the streaming setting is nontrivial ...
research
10/09/2018

Guess Free Maximization of Submodular and Linear Sums

We consider the problem of maximizing the sum of a monotone submodular f...
research
12/20/2019

Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout Classification

Semmelhack et al. (2014) have achieved high classification accuracy in d...

Please sign up or login with your details

Forgot password? Click here to reset