<p><u>Abstract:</u></p><p>With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law enforcement, etc. has raised serious concerns about fairness, accountability, trust and interpretability in machine learning algorithms. To alleviate this problem, we have developed D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases from tabular datasets. </p><p></p><p>D-Bias uses a graphical causal model to represent causal relationships among different features in the dataset and as a medium to inject domain knowledge. A user can detect the presence of bias against a group, say females, or a subgroup, say black females, by identifying unfair causal relationships in the causal network and using an array of fairness metrics. Thereafter, the user can mitigate bias by refining the causal model and acting on the unfair causal edges.</p><p></p><p>We found that D-BIAS helps reduce bias significantly compared to the baseline debiasing approach across different fairness metrics while incurring little data distortion and a small loss in utility. Moreover, our human-in-the-loop based approach significantly outperforms an automated approach on trust, interpretability and accountability</p><p></p><p><u>Bio:</u></p><p>Klaus Mueller received a PhD in computer science from The Ohio State University in 1998. He is currently a professor in the Computer Science Department at Stony Brook University and he is also a senior scientist at the Computational Science Initiative at Brookhaven National Lab. His current research interests are visual analytics, explainable AI, data science and medical imaging. He won the US National Science Foundation Early Career Award, the SUNY Chancellor Award for Excellence in Scholarship and Creative Activity, and the Meritorious Service Certificate and the Golden Core Award of the IEEE Computer Society. In 2018 Klaus was inducted into the National Academy of Inventors. To date, he has authored more than 300 peer-reviewed journal and conference papers, which have been cited more than 12,000 times. He is a frequent speaker at international conferences, has organized or participated in 18 tutorials on various topics, chaired the IEEE Visualization Conference in 2009, and was the elected chair of the IEEE Technical Committee on Visualization and Computer Graphics (VGTC) from 2012-2015. Klaus just finished his 4-year term as the Editor-in-Chief of IEEE Transactions on Visualization and Computer Graphics. He is a senior member of the IEEE.</p>
Friday, January 27, 2023 - 02:40pm to Friday, January 27, 2023 - 03:40pm
Seminar: Klaus Mueller: 'D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias'