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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction

Vinith M. Suriyakumar , Marzyeh Ghassemi , Berk Ustun

   Access Paper or Ask Questions

Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations

Hammaad Adam , Ming Ying Yang , Kenrick Cato , Ioana Baldini , Charles Senteio , Leo Anthony Celi , Jiaming Zeng , Moninder Singh , Marzyeh Ghassemi

* Accepted to the 2022 AAAI/ACM Conference on AI, Ethics, and Society (AIES '22), ACM, Oxford, UK, 2022 

   Access Paper or Ask Questions

The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations

Aparna Balagopalan , Haoran Zhang , Kimia Hamidieh , Thomas Hartvigsen , Frank Rudzicz , Marzyeh Ghassemi

* Published in FAccT 2022 

   Access Paper or Ask Questions

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud , Karsten Roth , Kimia Hamidieh , Nicolas Papernot , Marzyeh Ghassemi

* Published as a conference paper at ICLR 2022 

   Access Paper or Ask Questions

Improving the Fairness of Chest X-ray Classifiers

Haoran Zhang , Natalie Dullerud , Karsten Roth , Lauren Oakden-Rayner , Stephen Robert Pfohl , Marzyeh Ghassemi

* Published in CHIL 2022 

   Access Paper or Ask Questions

Semi-Markov Offline Reinforcement Learning for Healthcare

Mehdi Fatemi , Mary Wu , Jeremy Petch , Walter Nelson , Stuart J. Connolly , Alexander Benz , Anthony Carnicelli , Marzyeh Ghassemi

* Published at Conference on Health, Inference, and Learning (CHIL) 2022 

   Access Paper or Ask Questions

Learning Optimal Predictive Checklists

Haoran Zhang , Quaid Morris , Berk Ustun , Marzyeh Ghassemi

* Published in NeurIPS 2021 

   Access Paper or Ask Questions

Quantifying the Task-Specific Information in Text-Based Classifications

Zining Zhu , Aparna Balagopalan , Marzyeh Ghassemi , Frank Rudzicz

   Access Paper or Ask Questions

Medical Dead-ends and Learning to Identify High-risk States and Treatments

Mehdi Fatemi , Taylor W. Killian , Jayakumar Subramanian , Marzyeh Ghassemi

   Access Paper or Ask Questions

Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing

Sindhu C. M. Gowda , Shalmali Joshi , Haoran Zhang , Marzyeh Ghassemi

* Published in CIKM 2021 

   Access Paper or Ask Questions