Suis nous sur
Golnoosh Fanardi-BW_F

Golnoosh Farnadi


  • Titulaire de chaire en IA Canada-CIFAR
  • Stratégie pancanadienne en matière d’IA



À Propos

The increasing use of algorithmic decision making in domains that affect people’s lives such as employment, education, policing and loan approval, has raised concerns about possible biases and discrimination that such systems might introduce. Recent concerns about algorithmic discrimination have motivated the development of fairness-aware mechanisms in the machine learning (ML) community and the operations research (OR) community, independently. While in fairness-aware ML, the focus is usually on ensuring that the predictions made by a learned model are fair, in reality the fairness should be guaranteed for the decisions made using such predictions. Existing methods in fairness-aware optimization resolve this issue, however they are often deterministic and fall short in exploiting the knowledge which is available in data. Golnoosh Farnadi’s research focuses on the complementary strengths of fairness methods in ML and OR to address these shortcomings in a fair data-driven decision making system.


  • Bourse postdoctorale, IVADO, 2018-2021
  • Prix du meilleur article, atelier Beyond online data, ICWSM, 2018
  • Prix du meilleur article, atelier Beyond online data, ICWSM, 2018

Publications Pertinentes

  • A. Sivaraman, G. Farnadi, T. Millstein, G. Van den Broeck. « Counterexample-guided learning of monotonic neural networks », Advances in Neural Information Processing Systems 33 (NeurIPS 2020).
  • G. Farnadi, B. Babaki, M. Gendreau. « A unifying framework for fairness-aware influence maximization », Companion Proceedings of the Web Conference 2020, p. 714-722, avril 2020.
  • Y. Choi, G. Farnadi, B. Babaki, G. Van den Broeck. « Learning fair naive bayes classifiers by discovering and eliminating discrimination patterns », Proceedings of the AAAI Conference on Artificial Intelligence, 34(06):10077-10084, avril 2020.
  • G. Farnadi, B. Babaki, L. Getoor. « Fairness in relational domains », Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, p. 108-114, décembre 2018.


Le CIFAR est un organisme de bienfaisance enregistré qui reçoit le soutien des gouvernements du Canada, de l’Alberta et du Québec, ainsi que de fondations, de donateurs individuels, d’entreprises et de partenaires canadiens et internationaux.

Centre MaRS, tour Ouest
661, avenue University, bureau 505
Toronto (Ontario) M5G 1M1 Canada