Events

Global AI Frontier Lab Seminar Series: SHAP-based Explanations are Sensitive to Feature Representation (ACM FAccT 2025)

Speaker: Hyunseung Hwang

Location: 1 MetroTech Center

Date: Monday, October 6, 2025

We are pleased to announce the next fall session of the Global AI Frontier Lab: Seminar Series on October 6, 2025. Hyunseung Hwang will be presenting on "SHAP-based Explanations are Sensitive to Feature Representation (ACM FAccT 2025)". Dinner & networking will begin at 6:00 PM and the seminar will start at 7:00 PM EST. The seminar will be held at the
Global AI Frontier Lab at 1 Metrotech Center, Brooklyn, NY 11201. This event will be in-person & online. In-person attendance is strongly encouraged for Lab researchers in NYC. Please RSVP by filling out this Google Form. For online attendees, a Zoom link will be sent out prior to the event. Please reach out to global-ai-frontier-lab@nyu.edu with any questions. We hope to see you there!Bio: Hyunseung Hwang is a Ph.D. candidate in Electrical Engineering at KAIST, specializing in machine learning interpretability and explainability. His research critically investigates explanation techniques that are often taken for granted, exposing their limitations and proposing more robust, transparent alternatives. His major work, XClusters: Explainability-First Clustering, introduces a novel framework that prioritizes interpretability in unsupervised learning by generating time series cluster explanations grounded in domain knowledge and feature attributions. He also studies how tools like SHAP can be subtly manipulated, with implications for fairness and trust in AI systems. Explainability of AI applications is crucial in decision-making processes where the risk of incorrect predictions influences individuals, groups, and governments. He seeks to build robust explanations that can lead to decisions with high confidence to prevent such risks.