David I. Inouye

David I. Inouye works on machine learning methods that generate and transform data (generative modeling), explain model decisions, and remain reliable when data distributions shift or contain spurious patterns. His work often combines ideas from causal inference, fairness, and robustness with practical tools like generative models, flow-based methods, and explainability techniques, applied to areas such as image data, graphs, and federated (distributed) learning settings.

Publication output has grown fairly steadily over the last decade, rising from a couple of papers per year in 2017-2018 to a sustained average of about 5 per year since 2021, with peaks in 2023 and 2025.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026