Past Events

Qualifying Exam

ABCinML: Anticipatory Bias Correction in Machine Learning


Download as iCal file

Tuesday, December 21, 2021, 09:00am - 10:30am


Speaker: Abdulaziz A. Almuzaini

Location : Via Zoom


Vivek K. Singh (Research advisor)

David M. Pennock

Amélie Marian

Srinivas Narayana

Event Type: Qualifying Exam

Abstract: Static models (i.e., train once, deploy forever) of machine learning (ML) rarely work in practical settings. Besides fluctuations in accuracy over time, they are likely to suffer from biases based on the poor representations or past injustices coded in human judgements. Thus, multiple researchers have begun to explore ways to maintain algorithmic fairness over time. One line of work focuses on”dynamic learning” i.e., retraining after each batch, and the other on ”robustlearning” which tries to make the algorithms robust across all possible future challenges. Robust learning often yields to (overly) conservative models and ”dynamic learning” tries to reduce biases soon after, they have occurred. We propose an anticipatory ”dynamic learning” approach for correcting the algorithm to prevent bias before it occurs. Specifically, we make use of anticipations regarding the relative distributions of population subgroups (e.g., relative ratio of maleand female applicants) in the next cycle to identify the right parameters for an importance weighing fairness approach. Results from experiments over multiple real-world datasets suggest that this approach has a promise for anticipatory bias correction.


Rutgers University School of Arts and Sciences

Contact  Vivek K. Singh

Meeting ID: 914 3106 3942
Password: 670928