Timezone: »
In this paper we propose a novel method that provides contrastive explanations justifying the classification of an input by a black box classifier such as a deep neural network. Given an input we find what should be minimally and sufficiently present (viz. important object pixels in an image) to justify its classification and analogously what should be minimally and necessarily \emph{absent} (viz. certain background pixels). We argue that such explanations are natural for humans and are used commonly in domains such as health care and criminology. What is minimally but critically \emph{absent} is an important part of an explanation, which to the best of our knowledge, has not been explicitly identified by current explanation methods that explain predictions of neural networks. We validate our approach on three real datasets obtained from diverse domains; namely, a handwritten digits dataset MNIST, a large procurement fraud dataset and a brain activity strength dataset. In all three cases, we witness the power of our approach in generating precise explanations that are also easy for human experts to understand and evaluate.
Author Information
Amit Dhurandhar (IBM Research)
Pin-Yu Chen (IBM Research AI)
Ronny Luss (IBM Research)
Chun-Chen Tu (University of Michigan)
Paishun Ting (University of Michigan)
Karthikeyan Shanmugam (IBM Research, NY)
Payel Das (IBM Research)
More from the Same Authors
-
2020 Poster: Active Structure Learning of Causal DAGs via Directed Clique Trees »
Chandler Squires · Sara Magliacane · Kristjan Greenewald · Dmitriy Katz · Murat Kocaoglu · Karthikeyan Shanmugam -
2020 Poster: Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning »
Amin Jaber · Murat Kocaoglu · Karthikeyan Shanmugam · Elias Bareinboim -
2020 Poster: Model Agnostic Multilevel Explanations »
Karthikeyan Natesan Ramamurthy · Bhanukiran Vinzamuri · Yunfeng Zhang · Amit Dhurandhar -
2020 Poster: A Decentralized Parallel Algorithm for Training Generative Adversarial Nets »
Mingrui Liu · Wei Zhang · Youssef Mroueh · Xiaodong Cui · Jarret Ross · Tianbao Yang · Payel Das -
2020 Poster: Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions »
Matthew Faw · Rajat Sen · Karthikeyan Shanmugam · Constantine Caramanis · Sanjay Shakkottai -
2020 Poster: ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training »
Chia-Yu Chen · Jiamin Ni · Songtao Lu · Xiaodong Cui · Pin-Yu Chen · Xiao Sun · Naigang Wang · Swagath Venkataramani · Vijayalakshmi (Viji) Srinivasan · Wei Zhang · Kailash Gopalakrishnan -
2020 Poster: Learning Global Transparent Models consistent with Local Contrastive Explanations »
Tejaswini Pedapati · Avinash Balakrishnan · Karthikeyan Shanmugam · Amit Dhurandhar -
2020 Poster: CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models »
Vijil Chenthamarakshan · Payel Das · Samuel Hoffman · Hendrik Strobelt · Inkit Padhi · Kar Wai Lim · Benjamin Hoover · Matteo Manica · Jannis Born · Teodoro Laino · Aleksandra Mojsilovic -
2020 Poster: Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes »
Zaiwei Chen · Siva Theja Maguluri · Sanjay Shakkottai · Karthikeyan Shanmugam -
2020 Poster: Higher-Order Certification For Randomized Smoothing »
Jeet Mohapatra · Ching-Yun Ko · Tsui-Wei Weng · Pin-Yu Chen · Sijia Liu · Luca Daniel -
2020 Poster: Optimizing Mode Connectivity via Neuron Alignment »
Norman J Tatro · Pin-Yu Chen · Payel Das · Igor Melnyk · Prasanna Sattigeri · Rongjie Lai -
2020 Spotlight: Higher-Order Certification For Randomized Smoothing »
Jeet Mohapatra · Ching-Yun Ko · Tsui-Wei Weng · Pin-Yu Chen · Sijia Liu · Luca Daniel -
2020 Expo Talk Panel: AI against COVID-19 at IBM Research »
Divya Pathak · Payel Das · Michal Rosen-Zvi · Salim Roukos -
2019 Poster: Differentially Private Distributed Data Summarization under Covariate Shift »
Kanthi Sarpatwar · Karthikeyan Shanmugam · Venkata Sitaramagiridharganesh Ganapavarapu · Ashish Jagmohan · Roman Vaculin -
2019 Poster: Sample Efficient Active Learning of Causal Trees »
Kristjan Greenewald · Dmitriy Katz · Karthikeyan Shanmugam · Sara Magliacane · Murat Kocaoglu · Enric Boix Adsera · Guy Bresler -
2019 Poster: Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions »
Murat Kocaoglu · Amin Jaber · Karthikeyan Shanmugam · Elias Bareinboim -
2018 Poster: Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization »
Sijia Liu · Bhavya Kailkhura · Pin-Yu Chen · Paishun Ting · Shiyu Chang · Lisa Amini -
2018 Poster: Improving Simple Models with Confidence Profiles »
Amit Dhurandhar · Karthikeyan Shanmugam · Ronny Luss · Peder A Olsen -
2018 Poster: Efficient Neural Network Robustness Certification with General Activation Functions »
Huan Zhang · Tsui-Wei Weng · Pin-Yu Chen · Cho-Jui Hsieh · Luca Daniel -
2017 Poster: Experimental Design for Learning Causal Graphs with Latent Variables »
Murat Kocaoglu · Karthikeyan Shanmugam · Elias Bareinboim -
2017 Poster: Model-Powered Conditional Independence Test »
Rajat Sen · Ananda Theertha Suresh · Karthikeyan Shanmugam · Alexandros Dimakis · Sanjay Shakkottai -
2015 Poster: Learning Causal Graphs with Small Interventions »
Karthikeyan Shanmugam · Murat Kocaoglu · Alexandros Dimakis · Sriram Vishwanath -
2014 Poster: Sparse Polynomial Learning and Graph Sketching »
Murat Kocaoglu · Karthikeyan Shanmugam · Alexandros Dimakis · Adam Klivans -
2014 Poster: On the Information Theoretic Limits of Learning Ising Models »
Rashish Tandon · Karthikeyan Shanmugam · Pradeep Ravikumar · Alexandros Dimakis -
2014 Oral: Sparse Polynomial Learning and Graph Sketching »
Murat Kocaoglu · Karthikeyan Shanmugam · Alexandros Dimakis · Adam Klivans