log in  |  register  |  feedback?  |  help  |  web accessibility
Logo
Algorithmic Fairness in an Ever-Changing World
Furong Huang - UMD
IRB 4105 and Zoom: https://umd.zoom.us/j/96516874709?pwd=RG0xMnQ4aWkzTVY4ZXNxZ09TQnJGQT09
Thursday, February 1, 2024, 2:00-3:15 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract
We explore the challenges of maintaining fairness in machine learning models amidst distribution shifts and sequential decision-making contexts. We scrutinize how traditional fairness approaches, predicated on stable training and test distributions, falter when applied to dynamic real-world scenarios, leading to fairness degradation. Addressing this, our work introduces innovative strategies, including a fair consistency regularization method and the Equal Long-term Benefit Rate concept, to adapt fairness principles to both instantaneous and long-term impacts. Through comprehensive analysis and experiments on synthetic and real datasets, we demonstrate the effectiveness of these methods in robustly transferring fairness and reducing bias, while maintaining high utility in various environments.
Bio

Furong Huang is an Assistant Professor of the Department of Computer Science at University of Maryland. She received her Ph.D. in electrical engineering and computer science from UC Irvine in 2016, after which she spent one year as a postdoctoral researcher at Microsoft Research NYC. She works on statistical and trustworthy machine learning, foundation models and reinforcement learning, with specialization in domain adaptation, algorithmic robustness and fairness. With a focus on high-dimensional statistics and sequential decision-making, she develops efficient, robust, scalable, sustainable, ethical and responsible machine learning algorithms. She is recognized for her contributions with awards including best paper awards, the MIT Technology Review Innovators Under 35 Asia Pacific, the MLconf Industry Impact Research Award, the NSF CRII Award, the Microsoft Accelerate Foundation Models Research award, the Adobe Faculty Research Award, three JP Morgan Faculty Research Awards and Finalist of AI in Research - AI researcher of the year for Women in AI Awards North America.

This talk is organized by Emily Dacquisto