Human-centric Machine Learning

  • Consistent Estimators for Learning to Defer to an Expert
    Hussein Mozannar, David Sontag
    ICML 2020
    [paper] [ talk ] [ code GitHub ]

Algorithmic Fairness

  • Fair Learning with Private Demographic Data
    Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro
    ICML 2020 and NeurIPS 2019 Workshop on Machine Learning with Guarantees
    [paper] [poster] [talk] [ code GitHub ]

  • From Fair Decision Making To Social Equality
    Hussein Mouzannar, Mesrob I. Ohannessian, Nathan Srebro
    Proceedings of the ACM 2019 Conference on Fairness, Accountability, and Transparency (ACM FAT* 2019)
    [paper] [slides] [talk, from min 20]

Applications of Machine Learning

  • Neural Arabic Question Answering
    Hussein Mozannar, Karl El Hajal, Elie Maamary, Hazem Hajj
    Proceedings of the Fourth Arabic Natural Language Processing Workshop at ACL 2019 (WANLP 2019)
    [paper] [code GitHub]

  • Damage Identification in Social Media Posts using Multimodal Deep Learning
    Hussein Mouzannar, Yara Rizk, Mariette Awad
    Proceedings of the 15th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2018)
    [ paper] [ code GitHub ] [ dataset UCI ]

Course Projects

  • Multi-Agent Reinforcement Learning: Transfer and Algorithms
    Hussein Mouzannar
    This was part of a semester long research project, I explored multi agent reinforcement algorithms that only take into consideration the top-k agents that have the most influence on them. This work was motivated by a future direction proposed by MADDPG
    [ draft ]