1

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

We provide a method to decide when to display suggestions in AI-assisted programming systems based on the programmer’s feedback. We show that we can avoid displaying a significant fraction of suggestions that would have been rejected.

Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Closing the Gap in High-Risk Pregnancy Care Using Machine Learning and Human-AI Collaboration

We build new machine learning algorithms that can predict whether a patient is pregnant and whether they will have a high-risk pregnancy. We then integrate these algorithms into a user interface and evaluate it with nurses.

Hussein Mozannar, Yuria Utsumi, Irene Y Chen, Stephanie S Gervasi, Michele Ewing, Aaron Smith-McLallen, David Sontag

Who Should Predict? Exact Algorithms For Learning to Defer to Humans

We provide algorithms that can provably minimize the learning to defer objective and provide an experimental benchmark to study human-deferral algorithms.

Hussein Mozannar, Hunter Lang, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag

Sample Efficient Learning of Predictors that Complement Humans

We characterize theoretically the gain from building ML classifiers that complement humans, show how do this by reducing any multiclass loss to a cost-sensitive loss and create human-label efficient algorithms based on active learning.

Mohammad-Amin Charusaie, Hussein Mozannar, David Sontag, Samira Samadi

Teaching Humans When To Defer to a Classifier via Exemplars

We develop an onboarding stage for teaching users when to rely on AI systems and when not to.

Hussein Mozannar, Arvind Satyanarayan, David Sontag

Consistent Estimators for Learning to Defer to an Expert

We develop learning algorithms based on novel surrogate losses that know when to predict and when to defer to a human.

Hussein Mozannar, David Sontag

Consistent Estimators for Learning to Defer to an Expert

Fair learning with private demographic data

We build a procedure to learn a fair predictor (e.g. satisfies equalized odds) when the demographic attributes are privatized.

Hussein Mozannar, Mesrob Ohannessian, Nathan Srebro

From fair decision making to social equality

The study of fairness in intelligent decision systems has mostly ignored long-term influence on the underlying population. Yet fairness …

Hussein Mouzannar, Mesrob I Ohannessian, Nathan Srebro

Neural Arabic Question Answering

We develop learning algorithms based on novel surrogate losses that know when to predict and when to defer to a human.

Hussein Mozannar, Karl El Hajal, Elie Maamary, Hazem Hajj

Damage Identification in Social Media Posts using Multimodal Deep Learning

Social media has recently become a digital lifeline used to relay information and locate survivors in disaster situations. Currently, …

Hussein Mouzannar, Yara Rizk, Mariette Awad