63 citations · 90 across the 9 of their papers we have counts for
6 papers · 1 filter
Towards Explaining Distribution Shifts
Sean Kulinski, David I. Inouye
A distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models. Thus, un…
Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests
Sean Kulinski, Saurabh Bagchi, David I. Inouye
While previous distribution shift detection approaches can identify if a shift has occurred, these approaches cannot localize which specific features have caused a distribution shi…
Shapley Explanation Networks
Rui Wang, Xiaoqian Wang, David I. Inouye
Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on post-hoc Shapley explanations, which can be comp…
Exploring Adversarial Examples via Invertible Neural Networks
Ruqi Bai, Saurabh Bagchi, David I. Inouye
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability…
Automated Dependence Plots
David I. Inouye, Liu Leqi, Joon Sik Kim +2
In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to validate various qualitative properties of a model.…
On the (In)fidelity and Sensitivity for Explanations
Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala +2
We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been co…