Hello! my name is Yongsu Ahn. I’m a 5rd-year PhD Student in School of Computing and Information at University of Pittsburgh. I’m luckily advised by Dr. Yu-Ru Lin at PICSO Lab.
My research interest lies at the intersection of Visual analytics, Fair and Explainable AI, and Interactive machine learning. I’m studying how AI-based tools will better assist the important decision makings and information use in our society. For the heterogenous population users including data practioners, domain experts and lay users, I pursue AI for everyone to develop and promote human-centered AI that is fair, interpretable, and responsible as a viable tool.
News
| Jul, 2023 | Our paper, "VISPUR: Visual Aids for Identifying and Interpreting Spurious Associations in Data-Driven Decisions", was accepted to VIS 2023. |
| Dec, 2022 | Our paper "ESCAPE: Countering Systematic Errors from Machine’s Blind Spots via Interactive Visual Analysis" was accepted to CHI 2023! |
| Oct, 2022 | I presented our paper, "Improving Citizen-initiated Police Reform Efforts through Interactive Design: A Case Study in Allegheny" with Blair and Eliana at EAAMO 2022. It features our Allegeny County Policing Project investigating easy-to-navigate ways for citizens, researchers, and activists interested in more police accountability. |
| Nov, 2021 | Our team gave a talk in Year of Data and Society, "Grief to Action: Project Police Union Contacts". |
| Jan, 2021 | Our paper "PolicyFlow: Interpreting Policy Diffusion in Context" received the Best Paper Award for 2020 for ACM Transactions on Interactive Intelligent Systems! Read more about award and paper. |
| May, 2020 | I will be working as a research intern in Human-Machine Interaction team at Bosch. |
| Apr, 2019 | Two papers will be presented in IEEE VIS 2019, FairSight and FacIt. |
Publications
Human Valuation of Explanations in Decision-Aids
Break Out of a Pigeonhole: A Unified Framework for Examining Miscalibration, Bias, and Stereotype in Recommender Systems
HungerGist: An Interpretable Predictive Model for Food Insecurity
VISPUR: Visual Aids for Identifying and Interpreting Spurious Associations in Data-Driven Decisions
ESCAPE: Countering Systematic Errors from Machine’s Blind Spots via Interactive Visual Analysis
Improving Citizen-initiated Police Reform Efforts through Interactive Design: A Case Study in Allegheny County
Tribe or Not? Critical Inspection of Group Differences Using TribalGram
PolicyFlow: Interpreting Policy Diffusion in Context
FairSight: Visual analytics for fairness in decision making
FacIt: Factorizing Tensors into Interpretable and Scrutinizable Patterns
PolicyFlow: Interpreting Policy Diffusion in Context