activity
20172022
most citedRethinking Stability for Attribution-based Explanations

4 citations · 7 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG20224 cited

Rethinking Stability for Attribution-based Explanations

Chirag Agarwal, Nari Johnson, Martin Pawelczyk +4

As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are st…

cs.CV20211 cited

A Tale Of Two Long Tails

Daniel D'souza, Zach Nussbaum, Chirag Agarwal +1

As machine learning models are increasingly employed to assist human decision-makers, it becomes critical to communicate the uncertainty associated with these model predictions. Ho…

cs.LG2021

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

Sushant Agarwal, Shahin Jabbari, Chirag Agarwal +3

As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniq…

cs.CV20201 cited

SAM: The Sensitivity of Attribution Methods to Hyperparameters

Naman Bansal, Chirag Agarwal, Anh Nguyen

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input…

cs.LG2019

Explaining image classifiers by removing input features using generative models

Chirag Agarwal, Anh Nguyen

Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding no…

cs.CR2018

Improving Adversarial Robustness by Encouraging Discriminative Features

Chirag Agarwal, Anh Nguyen, Dan Schonfeld

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.…