Topic: Mitigating Bias in Data-driven Tasks

Next in our fall seminar series, we welcome Dr. Ke Yang from the University of Texas San Antonio.

Abstract:
Data-driven tasks are used in assisting decisions in many domains that greatly affect people’s lives. Though these tasks are efficient, they inevitably inherit bias in the input data and show problematic behaviors. Deploying unfair algorithms in critical domains will reinforce and legitimize the inequitable treatment of groups who are already disadvantaged. Moreover, the deployment of these tasks lacks transparency and accountability.
In this talk, I will introduce my research on mitigating bias in two types of data-driven tasks: rankings and classifications, which are frequently set up to automate decision-making processes. I will discuss three projects that demonstrate how fairness and diversity are ensured in ranking tasks. Then, I will talk about how fair classifications can be achieved by modeling bias as a data drift problem, which is a new approach to mitigate bias in classification tasks. At last, I will also highlight future work of promoting responsible data science by building solutions with the ethical concerns in the picture.

You can see the presentation live at UTSA San Pedro I room 530.

Those who cannot attend in-person are welcome to tune in virtually through Zoom: https://utsa.zoom.us/j/91049981814.