David I. Inouye

David I. Inouye is an Assistant Professor in the Elmore Family School of Electrical and Computer Engineering (ECE) at Purdue University. His research focuses on trustworthy AI/ML, causal inference, distribution robustness, and explainable AI. He holds a PhD in Computer Science from The University of Texas at Austin and completed a postdoc at Carnegie Mellon University.

Education:

• PostDoc in Machine Learning, 2019 – Carnegie Mellon University
• PhD in Computer Science, 2017 – The University of Texas at Austin
• MS in Computer Science, 2015 – The University of Texas at Austin
• BS in Electrical Engineering, 2012 – Georgia Institute of Technology
• BA in Natural Sciences, 2011 – Covenant College

Research Interests:

• Developing robust machine learning methods resilient to distribution shifts and computational assumptions
• Exploring causal mechanisms to mitigate ML robustness issues
• Advancing explainable AI and fairness in automated decision systems
• Designing robust collaborative learning frameworks for edge device networks

Publications Highlight Trends in:

• Counterfactual fairness and causal reasoning
• Federated learning and domain generalization
• Generative models and distribution matching
• Vertical data partitioning and dynamic network inference

Grants: Funded by NSF, Army Research Laboratory (ARL), and Office of Naval Research (ONR). Active lab collaborations include projects on federated domain translation and causal ML.

Labs/Teams: Leads the Inouye Lab, with contributions to open-source tools like FedINB and StarCraftImage datasets.