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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Downstream Fairness Caveats with Synthetic Healthcare Data


Mar 09, 2022
Karan Bhanot, Ioana Baldini, Dennis Wei, Jiaming Zeng, Kristin P. Bennett


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners


Feb 02, 2022
Karthikeyan Natesan Ramamurthy, Amit Dhurandhar, Dennis Wei, Zaid Bin Tariq


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FROTE: Feedback Rule-Driven Oversampling for Editing Models


Jan 06, 2022
Öznur Alkan, Dennis Wei, Massimiliano Mattetti, Rahul Nair, Elizabeth M. Daly, Diptikalyan Saha

* 23 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets


Dec 07, 2021
Kofi Arhin, Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Moninder Singh

* 15 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Interpretable and Fair Boolean Rule Sets via Column Generation


Nov 16, 2021
Connor Lawless, Sanjeeb Dash, Oktay Gunluk, Dennis Wei

* arXiv admin note: substantial text overlap with arXiv:2107.01325, arXiv:1805.09901 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

AI Explainability 360: Impact and Design


Sep 24, 2021
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang

* arXiv admin note: text overlap with arXiv:1909.03012 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Your fairness may vary: Group fairness of pretrained language models in toxic text classification


Aug 03, 2021
Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Mikhail Yurochkin, Moninder Singh


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Treatment Effect Estimation using Invariant Risk Minimization


Mar 13, 2021
Abhin Shah, Kartik Ahuja, Karthikeyan Shanmugam, Dennis Wei, Kush Varshney, Amit Dhurandhar


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Optimal Policies for the Homogeneous Selective Labels Problem


Nov 02, 2020
Dennis Wei

* 12 pages, 1 figure. To be presented at the Workshop on Consequential Decision Making in Dynamic Environments at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks


Oct 18, 2020
Dennis Wei, Tian Gao, Yue Yu

* 40 pages, 8 figures, to appear at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>