An adaptive ensemble imputer for lightweight streaming imputation in resource constrained environments
Discover Applied Sciences · 04.06.2026 · 8 (8)
DOI: 10.1007/s42452-026-08749-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Discover Applied Sciences, online erschienen am 04.06.2026. Verfasst von Ushashree P und 1 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Handling of missing values in a resource-constrained settings is more challenging when dealing with streaming because traditional methods (KNN, MICE) are computationally expensive online, while basic approaches (mean imputation) miss temporal dynamics and concept drift. A lightweight per-feature streaming ensemble method Adaptive Ensemble Imputer is proposed combining simple candidate imputers–exponential moving average (EMA), running mean, last observed value, short-window median. The weights are adapted online via occasional masked validation. The method maintains O(d) per-sample complexity and O(kd) memory (four candidates per feature), enabling real-time deployment on constrained settings. Evaluated on five benchmark data streams (Electricity, Poker, Covtype, MovingRBF, Rotating Hyperplane) under controlled MNAR mechanisms with repeated stratified runs, the method achieves \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$14.7\times $$\end{document} speedup over KNN, competitive accuracy with mean imputation on temporal data, and 37.5% faster downstream drift detection latency. Performance is mechanism-dependent: temporal-shift MNAR shows \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$-\,53$$\end{document}% MAE improvement (attributed to EMA emphasis when anomalies coincide with missingness), while level-dependent MNAR shows \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$+262$$\end{document}% degradation (systematic selection bias not corrected by adaptive weighting). The method does not provide theoretical MNAR unbiasedness guarantees; practitioners should use inverse-probability weighting for applications requiring MNAR correction. The primary contribution is computationally efficient, drift-responsive imputation suitable for streaming scenarios with temporal autocorrelation and concept drift.
Zitieren
APA
P, U., & Subramanyam, R. B. V. (2026). An adaptive ensemble imputer for lightweight streaming imputation in resource constrained environments. Discover Applied Sciences, 8(8). https://doi.org/10.1007/s42452-026-08749-0
Vancouver
P U, Subramanyam RBV. An adaptive ensemble imputer for lightweight streaming imputation in resource constrained environments. Discover Applied Sciences. 2026;8(8). doi:10.1007/s42452-026-08749-0
BibTeX
@article{P2026,
author = {P, Ushashree and Subramanyam, R. B. V.},
title = {An adaptive ensemble imputer for lightweight streaming imputation in resource constrained environments},
journal = {Discover Applied Sciences},
year = {2026},
volume = {8},
number = {8},
doi = {10.1007/s42452-026-08749-0}
}
EUVIMED