Meta-LSTM-Affine: A Memory-Based Meta-Adaptive Affine Modeling Framework for Non-Stationary Systems
Electronics · 08.05.2026 · 15 (10) · 1990
DOI: 10.3390/electronics15101990 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 08.05.2026. Verfasst von Yang-Ta Kao und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Modeling non-stationary systems with dynamically evolving data distributions remains a fundamental challenge in modern learning and optimization problems. In this work, we adopt a generalized notion of non-stationarity, where distribution shifts across tasks and domains are treated as forms of non-stationary processes. This perspective allows us to study non-stationary behavior in controlled settings such as Few-Shot Learning (FSL) and Source-Free Domain Adaptation (SFDA), where data distributions vary across episodes or domains. Conventional normalization and feature modulation strategies often rely on batch-level statistics, leading to unstable behavior under small-batch, streaming, and distribution-shifted conditions. To address these limitations, we propose Meta-LSTM-Affine, a memory-based meta-adaptive affine modeling (normalization) framework that unifies recurrent temporal memory and meta-learning for robust feature modulation. Unlike batch-statistics-driven normalization, our method employs an LSTM-based affine parameter generator (APG) to dynamically produce channel-wise scale and shift parameters based on both current inputs and historical context. To further enhance task-level adaptability, we introduce three lightweight meta-learning mechanisms—Meta-Initialization, Meta-Conditioning, and Meta-Update—that enable rapid cross-task adaptation without modifying the backbone. A bi-level training strategy with temporal smoothness regularization ensures stable affine parameter dynamics under distributional shifts. We validate Meta-LSTM-Affine on FSL and SFDA benchmarks, including Omniglot, MiniImageNet, TieredImageNet, Office-31, MNIST, SVHN, and USPS. Experimental results show that our method consistently outperforms existing approaches such as BN, MetaBN, MetaAFN, and LSTM-Affine, achieving improved stability and adaptation performance with minimal additional computational overhead. Overall, Meta-LSTM-Affine provides a stable and efficient affine modeling mechanism for learning under generalized non-stationary conditions without relying on batch-level statistics. This generalized formulation of non-stationarity allows us to study distributional changes in controlled and widely used benchmark settings, while maintaining relevance to real-world scenarios such as streaming data, continual learning, and time-evolving environments.
Zitieren
APA
Kao, Y., Tu, C., Lin, H. J., & Tokuyama, Y. (2026). Meta-LSTM-Affine: A Memory-Based Meta-Adaptive Affine Modeling Framework for Non-Stationary Systems. Electronics, 15(10), 1990. https://doi.org/10.3390/electronics15101990
Vancouver
Kao Y, Tu C, Lin HJ, Tokuyama Y. Meta-LSTM-Affine: A Memory-Based Meta-Adaptive Affine Modeling Framework for Non-Stationary Systems. Electronics. 2026;15(10):1990. doi:10.3390/electronics15101990
BibTeX
@article{Kao2026,
author = {Kao, Yang-Ta and Tu, Ching-Ting and Lin, Hwei Jen and Tokuyama, Yoshimasa},
title = {Meta-LSTM-Affine: A Memory-Based Meta-Adaptive Affine Modeling Framework for Non-Stationary Systems},
journal = {Electronics},
year = {2026},
volume = {15},
number = {10},
pages = {1990},
doi = {10.3390/electronics15101990}
}
EUVIMED