Time: 12:30 PM, September 27th (Friday), 2024
Location: POTR 234
Coffee and bagels will be provided.
Debugging and Explaining Unfairness in Machine Learning Models
Romila Pradhan, Assistant Professor, Department of Computer and Information Technology, Purdue University
Algorithmic decision-making systems continue to garner concerns regarding the perpetuation of systemic biases reflected in their training data. Discriminatory outcomes violate human rights and undermine public trust in automated decision-making. This talk will describe our efforts toward rendering AI-based systems less biased. We present Gopher, a causal data-based explanation mechanism, that allows us to diagnose the outcomes of a machine learning model and detect subsets of the training data most responsible for biased decisions. Gopher quantifies and approximates the causal responsibility of subsets and prunes the huge search space to generate compact, interpretable, and causal explanations for biased model predictions.
Dr. Pradhan is an Assistant Professor in the Department of Computer and Information Technology at Purdue University and leads the Responsible Data Science Lab where she and her students build trustworthy and responsible data-driven decision-making systems. Her research is in the broader areas of databases and data management, and is driven by the need to design algorithms and develop solutions that facilitate system explainability, fairness, and transparency. Her research is supported by NSF, Google, and the Underwriters Laboratories. She is a recipient of a Google Research Scholar award (2022) and an NSF CAREER award (2023).