Abstract
Longitudinal data are valuable because people change. Yet the objectives used to learn from these data can inadvertently erase that change. In person-level contrastive learning, observations from the same person are treated as positives; as records grow, those positives can span increasingly distant---and increasingly different---behavioral states. More history can therefore produce not only more data, but broader invariance. We show that this distinction is fundamental. We separate \emph{record span}, how much history the learner sees, from \emph{supervision span}, how far across that history positive-pair supervision reaches. Across in-home sensing records spanning up to 2.7 years, broader supervision systematically suppresses recoverable changing-state information, even when the available history is held fixed. At the broadest span, less than 10\% of the information recoverable from an untrained encoder remains. Yet keeping positives local is not sufficient: as records grow, even distant states that are never paired become increasingly similar. Explicitly contrasting other observations from the same person reverses this loss without shortening the record, revealing a second route by which longitudinal scale can broaden invariance. Finally, we prospectively reproduce the supervision-span effect in 199 GLOBEM participants. Longitudinal scale therefore presents a choice: more history need not mean more invariance. By controlling what is held invariant as records grow, we can preserve the change that made the longitudinal data valuable in the first place.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Mahmood, R., Xu, X. "., Beattie, Z., Kaye, J., & Huang, D. Y. (2026). Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning. https://omanscience.com/en/articles/longer-records-broader-invariance-the-hidden-scaling-problem-in-longitudinal-contrastive-learning
MLA 9
Mahmood, Rameen, et al. "Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning." https://omanscience.com/en/articles/longer-records-broader-invariance-the-hidden-scaling-problem-in-longitudinal-contrastive-learning.
Chicago (author–date)
Mahmood, Rameen, Xuhai "Orson" Xu, Zachary Beattie, Jeffrey Kaye, and Danny Yuxing Huang. 2026. "Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning." https://omanscience.com/en/articles/longer-records-broader-invariance-the-hidden-scaling-problem-in-longitudinal-contrastive-learning.
Harvard
Mahmood, R., Xu, X. "., Beattie, Z., Kaye, J. and Huang, D. Y. (2026) 'Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning', Available at: https://omanscience.com/en/articles/longer-records-broader-invariance-the-hidden-scaling-problem-in-longitudinal-contrastive-learning.
Vancouver
Mahmood R, Xu X", Beattie Z, Kaye J, Huang DY. Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning. https://omanscience.com/en/articles/longer-records-broader-invariance-the-hidden-scaling-problem-in-longitudinal-contrastive-learning
IEEE
R. Mahmood, X. ". Xu, Z. Beattie, J. Kaye, and D. Y. Huang, "Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning," https://omanscience.com/en/articles/longer-records-broader-invariance-the-hidden-scaling-problem-in-longitudinal-contrastive-learning.