CS Events Monthly View
Qualifying ExamABCinML: Anticipatory Bias Correction in Machine Learning |
|
||
Tuesday, December 21, 2021, 09:00am - 10:30am |
|||
Speaker: Abdulaziz A. Almuzaini
Location : Via Zoom
Committee:
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.
Organization:
Rutgers University School of Arts and Sciences
Contact Vivek K. Singh
https://rutgers.zoom.us/j/91431063942?pwd=cjJZeDc5elg0eGhoRkt2NkhyMHpRdz09
Meeting ID: 914 3106 3942
Password: 670928
Department of Computer Science