Distributional Latent Variable Models With an Application in Active Cognitive Testing

• Published in: IEEE transactions on cognitive and developmental systems Vol. 17; no. 5; pp. 1212 - 1222
• Main Authors: Kasumba, Robert, Marticorena, Dom C.P., Pahor, Anja, Ramani, Geetha, Goffney, Imani, Jaeggi, Susanne M., Seitz, Aaron R., Gardner, Jacob R., Barbour, Dennis L.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Active machine learning; Autoencoders; Batteries; cognition; Correlation; Data acquisition; Data collection; Data models; executive function (EF); latent variable modeling (LVM); Learning; Mathematical models; Maximum likelihood estimation; Numerical models; Real time; Testing; Vectors
• ISSN: 2379-8920; 2379-8939
• DOI: 10.1109/TCDS.2025.3548962

Cognitive modeling commonly relies on asking participants to complete a battery of varied tests to estimate attention, working memory, and other latent variables. In many cases, these tests result in highly variable observation models. A near-ubiquitous approach is to repeat many observations for each test independently, resulting in a distribution of the outcomes from each test given to each subject. Latent variable models (LVMs), if employed, are only added after data collection. In this article, we explore the usage of LVMs to enable learning across many correlated variables simultaneously. We extend LVMs to the setting where observed data for each subject are a series of observations from many different distributions, rather than simple vectors to be reconstructed. By embedding test battery results for individuals in a latent space that is trained jointly across a population, we can leverage correlations both between disparate test data for a single participant and between multiple participants. We then propose an active learning framework that leverages this model to conduct more efficient cognitive test batteries. We validate our approach by demonstrating with real-time data acquisition that it performs comparably to conventional methods in making item-level predictions with fewer test items.