Jun Yuan

A Data Storyteller with a strong enthusiasm for AI fairness and human-centered decision-making.

prof_pic.png

Department of Data Science

New Jersey Institute of Technology

Newark, NJ 07102

I am a PhD candidate in Data Science, with a background in Mathematics and Statistics. My research interest lies in the intersection of human-centered AI and information visualization.

Currently, I am working on designing visual-conversational analytic interfaces for ranking interpretation on high-stake decision-making (e.g., student course evaluation, AI hiring practice); adapting Learning-to-rank for fairness, accountability, and transparency; adversarial attacks and detection on explainable AI methods; information-seeking in crisis.

news

Sep 11, 2024 Our submission has been accepted to the VISxAI workshop at IEEEVIS24! The title is “TalkToRanker: A Conversational Interface for Ranking-based Decision-Making.”
Dec 16, 2023 Presented poster at the “XAI in action workshop at NeurIPS’23,” on the paper titled “A Simple Scoring Function to Fool SHAP: Stealing from the One Above.”
Nov 20, 2023 Awarded 3rd place at NJIT Research Day Competition 2023. :sparkles:
Sep 23, 2023 Presented poster at the “2023 Asian American Engineer of the Year Award Annual Convention” with the title “Ranking Al Visualization for Transparent Decision-making.”

selected publications

  1. foolSHAP.png
    A Simple Scoring Function to Fool SHAP: Stealing from the One Above
    Jun Yuan, and Aritra Dasgupta
    In NeurIPS23 Workshop of XAI in Action: Past, Present, and Future Applications , 2023
  2. contextual_transparency.png
    Introducing Contextual Transparency for Automated Decision Systems
    Mona Sloane, Ian René Solano-Kamaiko, Jun Yuan, Aritra Dasgupta, and Julia Stoyanovich
    Nature Machine Intelligence, 2023
  3. trivea.png
    TRIVEA: Transparent Ranking Interpretation Using Visual Explanation of Black-box Algorithmic Rankers
    Jun Yuan, Kaustav Bhattacharjee, Akm Zahirul Islam, and Aritra Dasgupta
    The Visual Computer, 2024