Date: Wednesday, March 5th, 2025
9:00 am – 10:00 am Pacific Time
12:00 pm – 1:00 pm Eastern Time
Location: Weekly Seminar, Zoom
Title: Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes
Abstract:
Statistical agencies rely on sampling techniques to collect socio-demographic data crucial for policy-making and resource allocation. This paper shows that surveys of important societal relevance introduce sampling errors that unevenly impact group-level estimates, thereby compromising fairness in downstream decisions. To address these issues, this paper introduces an optimization approach modeled on real-world survey design processes, ensuring sampling costs are optimized while maintaining error margins within prescribed tolerances. Additionally, privacy-preserving methods used to determine sampling rates can further impact these fairness issues. This paper explores the impact of differential privacy on the statistics informing the sampling process, revealing a surprising effect: not only is the expected negative effect from the addition of noise for differential privacy negligible, but also this privacy noise can in fact reduce unfairness as it positively biases smaller counts. These findings are validated over an extensive analysis using datasets commonly applied in census statistics.
This is joint work with Matt Williams, Ferdinando Fioretto, and Juba Ziani.
Bio:
Saswat Das is a Ph.D. student in Computer Science at the University of Virginia (UVA), advised by Ferdinando Fioretto. His research focuses on trustworthy and responsible AI, with an emphasis on differential privacy, contextual integrity, and algorithmic fairness. He is also interested in privacy risks and fairness challenges in the context of agentic large language models (LLMs). He has held research positions at Syracuse University and NISER, and his work on privacy and fairness has been presented at venues such as ICML and AAAI.
Joonhyuk Ko is an undergraduate student at the University of Virginia (UVA) studying computer science and mathematics. His research focuses on differential privacy and algorithmic fairness, with an interest in addressing various societal challenges in high-stakes decision-making tasks. He is a recipient of the Dean’s Undergraduate Engineering Research Fellowship from UVA and received an honorable mention for the CRA Outstanding Undergraduate Researcher Award.