A Hybrid Online-Offline Training Architecture for Maintaining Model Inference Freshness in Production Systems
Intelligent & Human Futures · 19.08.2026 · 2 (3) · 1-18
DOI: 10.63808/ihf.v2i3.472 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligent & Human Futures, online erschienen am 19.08.2026. Verfasst von Zhengyuan Wang. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Production drift erodes predictive performance between scheduled rebuilds. Periodic retraining incurs cadence-bound freshness lag, whereas continuous online learning is exposed to transient noise. We formalise inference freshness as observable sample lag plus a predictive-loss proxy and present a hybrid controller that coordinates online updates, offline rebuilds, and shadow-validated swaps. On four non-stationary INSECTS streams, the hybrid improves prequential accuracy by 1.1–5.3 percentage points over the stronger of periodic-offline and online-only. ARF remains 0.7–16.3 points more accurate but processes 455–610 predictions/s versus 6,231–9,820 for the hybrid in this CPU replay. A corrupted-rebuild test rejects all poor candidates and avoids a 20.63-point next-1,000-prediction regression. On synthetic low-, medium-, and high-transition streams, periodic retraining leads by 1.6, 2.9, and 0.5 points. The contribution is therefore a transparent freshness-aware scheduling and update-safety design, not state-of-the-art predictive performance.
Zitieren
APA
Wang, Z. (2026). A Hybrid Online-Offline Training Architecture for Maintaining Model Inference Freshness in Production Systems. Intelligent & Human Futures, 2(3), 1-18. https://doi.org/10.63808/ihf.v2i3.472
Vancouver
Wang Z. A Hybrid Online-Offline Training Architecture for Maintaining Model Inference Freshness in Production Systems. Intelligent & Human Futures. 2026;2(3):1-18. doi:10.63808/ihf.v2i3.472
BibTeX
@article{Wang2026,
author = {Wang, Zhengyuan},
title = {A Hybrid Online-Offline Training Architecture for Maintaining Model Inference Freshness in Production Systems},
journal = {Intelligent & Human Futures},
year = {2026},
volume = {2},
number = {3},
pages = {1--18},
doi = {10.63808/ihf.v2i3.472}
}
EUVIMED