Computer Science Speaking Skills Talk
Virtual Presentation - ET - Remote Access - Zoom
EMILY BLACK , Ph.D. StudentComputer Science DepartmentCarnegie Mellon University
Considering Process in Algorithmic Bias Detection and Mitigation
Artificial Intelligence (AI) systems now affect important decisions in people's lives, from the news articles they read, to whether or not they receive a loan. While the use of AI may lead to great accuracy and efficiency in the making of important decisions, recent news and research reports have shown that AI models can act unfairly: from exhibiting gender bias in hiring models, to racial bias in recidivism prediction systems.
In this talk, I will discuss methods for understanding fairness issues in AI through considering the process by which models arrive at their decisions. This technique contrasts with a large portion of AI fairness literature, which focuses on studying model outcomes alone. Specifically, I will show how considering a models end-to-end decision process allows us to expand our understanding of unfair behavior---such as in my work demonstrating how model instability can lead to unfairness by having important decisions rely on arbitrary modeling choices (e.g. whether or not a person is granted a loan from a decision-making model may depend on whether some unrelated person happened to be in the training set). Secondly, I will discuss how considering process can help us find bias mitigation techniques which avoid a tradeoff between predictive utility and fairness, with a case study from my collaboration with Stanford RegLab investigating tax auditing practices.
Presented in Partial Fulfillment of the CSD Speaking Skills Requirement.
Zoom Participation. See announcement.
For More Information: