Survey on Replay-Based Continual Learning and Empirical Validation on Feasibility in Diverse Edge Devices Using a Representative Method
Heon-Sung Park,
Hyeon-Chang Chu,
Min-Kyung Sung,
Chaewoon Kim,
Jeongwon Lee,
Dae-Won Kim () and
Jaesung Lee ()
Additional contact information
Heon-Sung Park: School of Computer Science and Engineering, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Hyeon-Chang Chu: School of Computer Science and Engineering, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Min-Kyung Sung: Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Chaewoon Kim: Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Jeongwon Lee: Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Dae-Won Kim: School of Computer Science and Engineering, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Jaesung Lee: Department of Artificial Intelligence, Chung-Ang University, Dongjak-gu, Seoul 06974, Republic of Korea
Mathematics, 2025, vol. 13, issue 14, 1-30
Abstract:
The goal of on-device continual learning is to enable models to adapt to streaming data without forgetting previously acquired knowledge, even with limited computational resources and memory constraints. Recent research has demonstrated that weighted regularization-based methods are constrained by indirect knowledge preservation and sensitive hyperparameter settings, and dynamic architecture methods are ill-suited for on-device environments due to increased resource consumption as the structure scales. In order to compensate for these limitations, replay-based continuous learning, which maintains a compact structure and stable performance, is gaining attention. The limitations of replay-based continuous learning are (1) the limited amount of historical training data that can be stored due to limited memory capacity, and (2) the computational resources of on-device systems are significantly lower than those of servers or cloud infrastructures. Consequently, designing strategies that balance the preservation of past knowledge with rapid and cost-effective updates of model parameters has become a critical consideration in on-device continual learning. This paper presents an empirical survey of replay-based continual learning studies, considering the nearest class mean classifier with replay-based sparse weight updates as a representative method for validating the feasibility of diverse edge devices. Our empirical comparison of standard benchmarks, including CIFAR-10, CIFAR-100, and TinyImageNet, deployed on devices such as Jetson Nano and Raspberry Pi, showed that the proposed representative method achieved reasonable accuracy under limited buffer sizes compared with existing replay-based techniques. A significant reduction in training time and resource consumption was observed, thereby supporting the feasibility of replay-based on-device continual learning in practice.
Keywords: continual learning; replay; sparse update; on-device; edge device (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:
Downloads: (external link)
https://www.mdpi.com/2227-7390/13/14/2257/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/14/2257/ (text/html)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:14:p:2257-:d:1700285
Access Statistics for this article
Mathematics is currently edited by Ms. Emma He
More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().