A leakage-controlled evaluation for meta-pretrained factorization machines in cold-start personalized learning
Frontiers in Psychology · 17.11.2026 · 17
DOI: 10.3389/fpsyg.2026.1908866 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Psychology, online erschienen am 17.11.2026. Verfasst von Jiayi Wu und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Cold-start educational recommendation must distinguish recovery of logged behavior from educational benefit. We evaluated a pooled factorization machine (Pooled FM) and a first-order meta-pretrained factorization machine (Meta-FM) on audited EdNet KT1 logs with 14,000 training, 3,000 development-validation, and 3,000 reserved test learners. Supports contain 1, 3, 5, or 10 complete bundle activities, and candidates comprise all 8,253 training-catalog bundles. Both methods share a sparse support-conditioned representation, matched initialization, a one-epoch training budget, and the same support-time evaluation update. The primary immediate deterministic endpoint is normalized discounted cumulative gain at rank 5 (nDCG@5), with three contrasts prespecified before held-out performance evaluation. Across five retained fitted seeds, held-out path nDCG@5 is 0.449031 ± 0.001990 for Pooled FM and 0.448597 ± 0.002068 for Meta-FM (mean ± sample standard deviation); the immediate bridge control is 0.445451. Meta-minus-Pooled is −0.000433969 [−0.000583808, −0.000289114], with a paired learner-cluster 95% interval. Pooled-minus-bridge is +0.003579978 [+0.002152788, +0.005165757] and Meta-minus-bridge is +0.003146009 [+0.001753661, +0.004723352]. These intervals condition on retained fitted seeds and the prespecified analysis; they do not quantify variability over new training runs. Earlier validation analyses show near-zero mean inference-update effects without proving equivalence and a material joint ordered-block/optimization effect under the matched budget. Prespecified stochastic validation and complementary Duolingo calibration remain separate endpoints; their held-out path utility is not established. The evidence supports careful horizon alignment and strong behavioral controls while avoiding general meta-training-superiority or causal learning-gain claims. No retraining, feature refitting, or test-driven selection occurred.
Zitieren
APA
Wu, J., & Xiong, Y. (2026). A leakage-controlled evaluation for meta-pretrained factorization machines in cold-start personalized learning. Frontiers in Psychology, 17. https://doi.org/10.3389/fpsyg.2026.1908866
Vancouver
Wu J, Xiong Y. A leakage-controlled evaluation for meta-pretrained factorization machines in cold-start personalized learning. Frontiers in Psychology. 2026;17. doi:10.3389/fpsyg.2026.1908866
BibTeX
@article{Wu2026,
author = {Wu, Jiayi and Xiong, Yi},
title = {A leakage-controlled evaluation for meta-pretrained factorization machines in cold-start personalized learning},
journal = {Frontiers in Psychology},
year = {2026},
volume = {17},
doi = {10.3389/fpsyg.2026.1908866}
}
EUVIMED