TAMIDS Tutorial Series: Theodora Chaspari: Exploring Fairness and Socio-demographic Bias in Machine Learning

Speaker: Theodora Chaspari, Ph.D. Assistant Professor, Computer Science & Engineering, Texas A&M University


Faculty Host: Yu Ding, TAMIDS

Abstract: Recent converging advances in sensing and computing allow the ambulatory long-term tracking of individuals yielding a rich set of real-life multimodal bio-behavioral measurements, such as speech, physiology, and facial expressions. While bio-behavioral measurements coupled with machine learning algorithms have been heralded as promising solutions to empowering physical and mental healthcare, various ethical and societal challenges prevent the widespread adoption of such technologies. One such challenge is that machine learning algorithms might be driven by and potentially further perpetuate existing socio-demographic disparities. The first part of this tutorial will cover recent studies exploring ways in which algorithms might reproduce socio-demographic disparities related to gender, race, and socio-economic status (SES). The second part of the tutorial will outline ways to mitigate unwanted bias, including iterative data re-labelling, fairness regularization, and adversarial learning to reduce evidence of sensitive attributes in the data.

Biography: Dr. Theodora Chaspari is an Assistant Professor in the Computer Science & Engineering Department at Texas A&M University. She has received her Bachelor of Science (2010) in Electrical & Computer Engineering from the National Technical University of Athens, Greece and her Master of Science (2012) and Ph.D. (2017) in Electrical Engineering from the University of Southern California. Dr. Chaspari’s research interests lie in the areas of affective computing, signal processing, data science, and machine learning. Papers co-authored with her students have been nominated and won awards at the ACM BuildSys 2019, IEEE ACII 2019, ASCE i3CE 2019, and IEEE BSN 2018 conferences. Dr. Chaspari’s reserarch is supported by federal and private funding sources (NSF, NIH, IARPA, AFRL, EiF, TAMU DoR).

Link to pdf version

You can also click this link to join the seminar

This image has an empty alt attribute; its file name is tamidsFooter-1024x81.jpg

For more information about TAMIDS seminar series, please contact Ms. Jennifer South at jsouth@tamu.edu