M.S. Final Oral Exam: Sumon Biswas

Event
Speaker: 
Sumon Biswas
Thursday, November 4, 2021 - 3:30pm
Location: 
Virtual
Event Type: 

Understanding Unfairness and its Mitigation in Open-Source Machine Learning Models

Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so on. It is important to ensure the fairness of these models so that no discrimination is made based on \textit{protected attributes} (e.g., race, sex, age) while decision making. Many such algorithmic fairness issues of machine learning software have been reported in the recent past. Research has been conducted to measure unfairness and mitigate that to a certain extent. What unfairness issues exist in open-source models and how do the mitigation techniques perform? In this thesis, we have focused on the empirical evaluation of fairness and mitigations on real-world machine learning models. We have created a benchmark of 40 top-rated models from Kaggle used for 5 different tasks, and then using a comprehensive set of fairness metrics, evaluated their fairness. Then, we have applied 7 mitigation techniques on these models and analyzed the fairness, mitigation results, and impacts on performance. We have found that some model optimization techniques result in inducing unfairness in the models. On the other hand, although there are some fairness control mechanisms in machine learning libraries, they are not documented. The mitigation algorithm also exhibit common patterns such as mitigation in the post-processing is often costly (in terms of performance) and mitigation in the pre-processing stage is preferred in most cases. We have also presented different trade-off choices of fairness mitigation decisions. Our study suggests future research directions to reduce the gap between theoretical fairness aware algorithms and the software engineering methods to leverage them in practice.

Committee: Hridesh Rajan (major professor), Andrew Miner, and Simanta Mitra

Join on Zoom: https://iastate.zoom.us/j/95172623927 Or, go to https://iastate.zoom.us/join and enter meeting ID: 951 7262 3927 Join from dial-in phone line: Dial: +1 312 626 6799 or +1 646 876 9923 Meeting ID: 951 7262 3927 Participant ID: Shown after joining the meeting. International numbers available: https://iastate.zoom.us/u/aeGJ5jRlfJ