Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Kush R. Varshney

Kush R. Varshney

Socially Responsible AI Algorithms: Issues, Purposes, and Challenges


Jan 12, 2021
Lu Cheng, Kush R. Varshney, Huan Liu

Figure 1 for Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
Figure 2 for Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
Figure 3 for Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
Figure 4 for Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
* 45 pages, 7 figures 
  Access Paper or Ask Questions

Learning to Initialize Gradient Descent Using Gradient Descent


Dec 22, 2020
Kartik Ahuja, Amit Dhurandhar, Kush R. Varshney

Figure 1 for Learning to Initialize Gradient Descent Using Gradient Descent
Figure 2 for Learning to Initialize Gradient Descent Using Gradient Descent
Figure 3 for Learning to Initialize Gradient Descent Using Gradient Descent
Figure 4 for Learning to Initialize Gradient Descent Using Gradient Descent

  Access Paper or Ask Questions

Empirical or Invariant Risk Minimization? A Sample Complexity Perspective


Oct 30, 2020
Kartik Ahuja, Jun Wang, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney

Figure 1 for Empirical or Invariant Risk Minimization? A Sample Complexity Perspective
Figure 2 for Empirical or Invariant Risk Minimization? A Sample Complexity Perspective
Figure 3 for Empirical or Invariant Risk Minimization? A Sample Complexity Perspective
Figure 4 for Empirical or Invariant Risk Minimization? A Sample Complexity Perspective

  Access Paper or Ask Questions

Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making


Oct 15, 2020
Charvi Rastogi, Yunfeng Zhang, Dennis Wei, Kush R. Varshney, Amit Dhurandhar, Richard Tomsett

* 15 pages, 5 figures 
  Access Paper or Ask Questions

Fair Data Integration


Jun 10, 2020
Sainyam Galhotra, Karthikeyan Shanmugam, Prasanna Sattigeri, Kush R. Varshney

Figure 1 for Fair Data Integration
Figure 2 for Fair Data Integration
Figure 3 for Fair Data Integration
Figure 4 for Fair Data Integration

  Access Paper or Ask Questions

Invariant Risk Minimization Games


Mar 18, 2020
Kartik Ahuja, Karthikeyan Shanmugam, Kush R. Varshney, Amit Dhurandhar

Figure 1 for Invariant Risk Minimization Games
Figure 2 for Invariant Risk Minimization Games
Figure 3 for Invariant Risk Minimization Games
Figure 4 for Invariant Risk Minimization Games

  Access Paper or Ask Questions

Joint Optimization of AI Fairness and Utility: A Human-Centered Approach


Feb 05, 2020
Yunfeng Zhang, Rachel K. E. Bellamy, Kush R. Varshney

Figure 1 for Joint Optimization of AI Fairness and Utility: A Human-Centered Approach
Figure 2 for Joint Optimization of AI Fairness and Utility: A Human-Centered Approach
Figure 3 for Joint Optimization of AI Fairness and Utility: A Human-Centered Approach
Figure 4 for Joint Optimization of AI Fairness and Utility: A Human-Centered Approach
* To appear in AIES 2020 proceedings 
  Access Paper or Ask Questions

Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies


Dec 05, 2019
Shivashankar Subramanian, Ioana Baldini, Sushma Ravichandran, Dmitriy A. Katz-Rogozhnikov, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Kush R. Varshney, Annmarie Wang, Pradeep Mangalath, Laura B. Kleiman

Figure 1 for Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies
Figure 2 for Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies
Figure 3 for Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies

  Access Paper or Ask Questions

Preservation of Anomalous Subgroups On Machine Learning Transformed Data


Nov 09, 2019
Samuel C. Maina, Reginald E. Bryant, William O. Goal, Robert-Florian Samoilescu, Kush R. Varshney, Komminist Weldemariam

Figure 1 for Preservation of Anomalous Subgroups On Machine Learning Transformed Data
Figure 2 for Preservation of Anomalous Subgroups On Machine Learning Transformed Data
Figure 3 for Preservation of Anomalous Subgroups On Machine Learning Transformed Data
Figure 4 for Preservation of Anomalous Subgroups On Machine Learning Transformed Data
* 5 pages, 3 figures, 2 tables, submitted to icassp 2019 
  Access Paper or Ask Questions

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning


Oct 30, 2019
Michiel A. Bakker, Duy Patrick Tu, Humberto RiverΓ³n ValdΓ©s, Krishna P. Gummadi, Kush R. Varshney, Adrian Weller, Alex Pentland

Figure 1 for DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
Figure 2 for DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
* Accepted at NeurIPS 2019 HCML Workshop 
  Access Paper or Ask Questions

Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets


Oct 29, 2019
Newton M. Kinyanjui, Timothy Odonga, Celia Cintas, Noel C. F. Codella, Rameswar Panda, Prasanna Sattigeri, Kush R. Varshney

Figure 1 for Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
Figure 2 for Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
Figure 3 for Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
Figure 4 for Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
* NeurIPS 2019 Workshop on Fair ML for Health 
  Access Paper or Ask Questions

An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy


Oct 17, 2019
Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney

Figure 1 for An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy
Figure 2 for An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy
Figure 3 for An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy

  Access Paper or Ask Questions

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques


Sep 14, 2019
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang

Figure 1 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Figure 2 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Figure 3 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Figure 4 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

  Access Paper or Ask Questions

How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?


Sep 08, 2019
Yaoli Mao, Dakuo Wang, Michael Muller, Kush R. Varshney, Ioana Baldini, Casey Dugan, AleksandraMojsilović

Figure 1 for How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?
Figure 2 for How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?

  Access Paper or Ask Questions

Characterization of Overlap in Observational Studies


Jul 09, 2019
Fredrik D. Johansson, Dennis Wei, Michael Oberst, Tian Gao, Gabriel Brat, David Sontag, Kush R. Varshney

Figure 1 for Characterization of Overlap in Observational Studies
Figure 2 for Characterization of Overlap in Observational Studies
Figure 3 for Characterization of Overlap in Observational Studies
Figure 4 for Characterization of Overlap in Observational Studies

  Access Paper or Ask Questions

Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning


Jun 05, 2019
Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush R. Varshney, Dennis Wei, Aleksandra Mojsilović

Figure 1 for Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
Figure 2 for Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
* presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA. arXiv admin note: substantial text overlap with arXiv:1805.11648 
  Access Paper or Ask Questions

Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines


May 08, 2019
Chirag Nagpal, Dennis Wei, Bhanukiran Vinzamuri, Monica Shekhar, Sara E. Berger, Subhro Das, Kush R. Varshney

Figure 1 for Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
Figure 2 for Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
Figure 3 for Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
Figure 4 for Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines

  Access Paper or Ask Questions

Bias Mitigation Post-processing for Individual and Group Fairness


Dec 14, 2018
Pranay K. Lohia, Karthikeyan Natesan Ramamurthy, Manish Bhide, Diptikalyan Saha, Kush R. Varshney, Ruchir Puri

Figure 1 for Bias Mitigation Post-processing for Individual and Group Fairness
Figure 2 for Bias Mitigation Post-processing for Individual and Group Fairness
Figure 3 for Bias Mitigation Post-processing for Individual and Group Fairness
Figure 4 for Bias Mitigation Post-processing for Individual and Group Fairness
* 5 pages, 4 figures 
  Access Paper or Ask Questions

Understanding Unequal Gender Classification Accuracy from Face Images


Nov 30, 2018
Vidya Muthukumar, Tejaswini Pedapati, Nalini Ratha, Prasanna Sattigeri, Chai-Wah Wu, Brian Kingsbury, Abhishek Kumar, Samuel Thomas, Aleksandra Mojsilovic, Kush R. Varshney

Figure 1 for Understanding Unequal Gender Classification Accuracy from Face Images
Figure 2 for Understanding Unequal Gender Classification Accuracy from Face Images
Figure 3 for Understanding Unequal Gender Classification Accuracy from Face Images
Figure 4 for Understanding Unequal Gender Classification Accuracy from Face Images

  Access Paper or Ask Questions

TED: Teaching AI to Explain its Decisions


Nov 12, 2018
Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush R. Varshney, Dennis Wei, Aleksandra Mojsilovic

Figure 1 for TED: Teaching AI to Explain its Decisions
Figure 2 for TED: Teaching AI to Explain its Decisions
Figure 3 for TED: Teaching AI to Explain its Decisions
* This article leverages some content from arXiv:1805.11648 
  Access Paper or Ask Questions

SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy


Nov 03, 2018
Minh N. B. Nguyen, Samuel Thomas, Anne E. Gattiker, Sujatha Kashyap, Kush R. Varshney

Figure 1 for SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy
Figure 2 for SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy
Figure 3 for SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy
Figure 4 for SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy

  Access Paper or Ask Questions

AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias


Oct 03, 2018
Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilovic, Seema Nagar, Karthikeyan Natesan Ramamurthy, John Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush R. Varshney, Yunfeng Zhang

Figure 1 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Figure 2 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Figure 3 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Figure 4 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
* 20 pages 
  Access Paper or Ask Questions

Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach


Sep 22, 2018
Ravi Kiran Raman, Roman Vaculin, Michael Hind, Sekou L. Remy, Eleftheria K. Pissadaki, Nelson Kibichii Bore, Roozbeh Daneshvar, Biplav Srivastava, Kush R. Varshney

Figure 1 for Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach
Figure 2 for Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach
Figure 3 for Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach
Figure 4 for Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach
* 16 pages, 8 figures 
  Access Paper or Ask Questions

Teaching Meaningful Explanations


Sep 11, 2018
Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush R. Varshney, Dennis Wei, Aleksandra Mojsilovic

Figure 1 for Teaching Meaningful Explanations
Figure 2 for Teaching Meaningful Explanations
Figure 3 for Teaching Meaningful Explanations
* 9 pages 
  Access Paper or Ask Questions

Increasing Trust in AI Services through Supplier's Declarations of Conformity


Aug 22, 2018
Michael Hind, Sameep Mehta, Aleksandra Mojsilovic, Ravi Nair, Karthikeyan Natesan Ramamurthy, Alexandra Olteanu, Kush R. Varshney


  Access Paper or Ask Questions

Teaching machines to understand data science code by semantic enrichment of dataflow graphs


Jul 16, 2018
Evan Patterson, Ioana Baldini, Aleksandra Mojsilovic, Kush R. Varshney

Figure 1 for Teaching machines to understand data science code by semantic enrichment of dataflow graphs
Figure 2 for Teaching machines to understand data science code by semantic enrichment of dataflow graphs
Figure 3 for Teaching machines to understand data science code by semantic enrichment of dataflow graphs
Figure 4 for Teaching machines to understand data science code by semantic enrichment of dataflow graphs
* 8 pages, 7 figures. To appear at the KDD '18 workshop on Fragile Earth: Theory Guided Data Science to Enhance Scientific Discovery 
  Access Paper or Ask Questions

Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018)


Jul 03, 2018
Been Kim, Kush R. Varshney, Adrian Weller


  Access Paper or Ask Questions