Wenbin Zhang

Assistant Professor, KFSCIS


Lecture Information:
  • October 27, 2023
  • 2:00 PM
  • CASE 241

Speaker Bio

Wenbin Zhang is an Assistant Professor in the Knight Foundation School of Computing & Information Sciences at Florida International University, and an Associate Member at the Te Ipu o te Mahara Artificial Intelligence Institute. His research investigates the theoretical foundations of machine learning with a focus on societal impact and welfare. In addition, he has worked in a number of application areas, highlighted by work on healthcare, geophysics, transportation, forestry, and finance. He is a recipient of the NSF CRII Award, and best paper awards at FAccT’23, ICDM’21 (best paper candidate) and DAMI (top 10 articles in 2022). He also regularly serves in the organizing committees across computer science and interdisciplinary venues, most recently Volunteer Chair at WSDM’24, Student Program Chair at AIES’23, and Student Travel Award Chair at ICDM’23.

Abstract

The significance of understanding and correcting algorithmic bias in machine learning (ML) has led to an increase in research on fairness in ML, which typically assumes that the underlying data is independent and identically distributed (IID). However, in reality, data is often represented using non-IID graph structures that capture connections among individual units. In this talk, I will motivate some of these challenges in fairness on graphs, and highlight some of our recent work on two topics including generative models and causal inference. I will also discuss the collaborative nature of fairness research, intersecting with privacy and security, software engineering, GeoAI, federated learning, LLM, etc., addressing issues like health disparity, housing discrimination and educational bias.