Xueru Zhang
Ohio State University, OH·Computer Science
Algorithms increasingly make decisions about people, from loans and hiring to college admissions. Climate models, meanwhile, struggle to anticipate fast-moving extremes.
- Fields
Computer Science
Engineering
Earth & Environmental Science
- Topics
machine learning
algorithmic fairness
strategic classification
- Grants
- 3 known grants, through Jul 2029
What they work on
- Model how individuals strategically and repeatedly change their behavior in response to fair machine learning decisions, using a sequential framework that combines stochastic control and game theory.
- Validate the human behavioral model and design interventions that improve long-term social welfare and equity in settings such as lending, hiring and admissions.
- Develop an analytical framework for human-AI interaction that covers safe training, safe deployment, alignment with social values and safe downstream effects, drawing on control theory and reinforcement learning.
- Design causal, interpretable interventions that keep human-AI feedback loops safe, testing them on recommendation, lending and healthcare use cases.
- Build the RI-M³T deep learning model, which combines vegetation, soil moisture, heat and atmospheric data, to forecast flash drought onset under changing climate conditions.
- Use model interpretability to quantify how vegetation-atmosphere interactions, memory effects and spatial connectivity drive flash droughts, and compare these relationships with Earth system models.
More about the research
The common thread in these projects is building machine learning systems that are reliable, interpretable and safe in a world that changes as they operate. In two projects, the change comes from people adapting to algorithms. In the third, it comes from interacting climate and vegetation conditions.
Why it matters
Algorithms used in lending, hiring, admissions, healthcare and recommendations can harm people over time as users adapt to them. This work could give designers and policymakers tools to keep such systems fair and safe over the long run. Better flash drought forecasts could give farmers, water-resource managers and communities earlier warning of crop losses, wildfire risk and water shortages.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Collaborative Research: CAIG: Leveraging Artificial Intelligence for understanding and forecasting flash drought development and propagation
NSF · Aug 2026 – Jul 2029
Collaborative Research: SLES: Long-Term Safety for Human-AI Ecosystem
NSF · Sep 2024 – Aug 2027
Collaborative Research: RI: AF: Small: Long-Term Impact of Fair Machine Learning under Strategic Individual Behavior
NSF · Oct 2022 – Sep 2026
Closest labs
Xueru Zhang
Ohio State University, OH·Computer Science
Build a mathematical model of how individuals strategically and repeatedly adapt to machine learning decision systems, and how this feeds back into model training. The model combines game theory and stochastic control.
Juba Ziani
Georgia Institute of Technology, GA·Computer Science·Early-career
Model how individual data providers shape the outcomes of machine learning systems through strategic choices about what data to share, combining tools from computer science and economics.
Himabindu Lakkaraju
Harvard University, MA·Computer Science·Early-career
Build theoretical and empirical frameworks that measure how faithfully leading explanation methods capture the behavior of different model classes, including linear and non-linear machine learning models.
The school
Ohio State University: 71 labs on PI Pages, $1.6B a year on research, 882 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.