log in  |  register  |  feedback?  |  help  |  web accessibility
Logo
PhD Defense: Exploring Diversity and Fairness in Machine Learning
Candice Schumann
Virtual: https://umd.zoom.us/j/96352453140 Password: 695603
Wednesday, May 6, 2020, 10:30 am-12:30 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract
With algorithms, artificial intelligence, and machine learning becoming increasingly ubiquitous in our society, we need to start thinking about the implications and ethical concerns of new models. In fact, two types of biases that impact machine learning models are social injustice bias (bias created by society) and measurement bias (bias created by unbalanced sampling). I believe that biases against groups of individuals found in machine learning models can be mitigated through the use of diversity and fairness constraints. This thesis introduces models to help humans make decisions in diverse and less biased ways.

This work starts with a call to action. Bias is rife in hiring and since algorithms are being used in multiple companies to filter applicants we need to pay special attention to this application. Inspired by this hiring application I introduce new multi-armed bandit frameworks to help assign human resources in the hiring process while enforcing diversity through a submodular utility function. Moving outside of hiring I present a contextual multi-armed bandit algorithm that enforces group fairness by learning a societal bias term and correcting for it. Additionally I take a look at fairness in traditional machine learning domain adaptation. Finally I explore extensions to my core work, delving into suicidality, comprehension of fairness definitions, and student evaluations.

Examining Committee: 
 
                           Chair:              Dr. John P. Dickerson          
                          Dean's rep:      Dr. Stuart N. Vogel
                          Members:        Dr.  Jeffrey S. Foster    
                                                    Dr. Hal Daume III
                                               Dr.  Alex Beutel  
Bio

Candice Schumann is a Ph.D. candidate at the University of Maryland, advised by Dr. John P. Dickerson. She received her B.S. in Computer Science and Mathematics from LaSalle University in 2014. She also received a Masters degree in Computer Science from the University of Maryland in 2018. Her research focuses on fairness and diversity in machine learning.

This talk is organized by Tom Hurst