CarM: Hierarchical Episodic Memory for Continual Learning

Soobee Lee, Minindu Weerakoon, Jonghyun Choi, Minjia Zhang, Di Wang, Myeongjae Jeon

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Continual Learning (CL) is an emerging machine learning paradigm in mobile or IoT devices that learns from a continuous stream of tasks. To avoid forgetting of knowledge of the previous tasks, episodic memory (EM) methods exploit a subset of the past samples while learning from new data. Despite the promising results, prior studies are mostly simulation-based and unfortunately do not promise to meet an insatiable demand for both EM capacity and system efficiency in practical system setups. We propose CarM, the first CL framework that meets the demand by a novel hierarchical EM management strategy. CarM has EM on high-speed RAMs for system efficiency and exploits the abundant storage to preserve past experiences and alleviate the forgetting by allowing CL to efficiently migrate samples between memory and storage. Extensive evaluations show that our method significantly outperforms popular CL methods while providing high training efficiency.

Original languageEnglish
Title of host publicationProceedings of the 59th ACM/IEEE Design Automation Conference, DAC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781450391429
Publication statusPublished - 2022 Jul 10
Event59th ACM/IEEE Design Automation Conference, DAC 2022 - San Francisco, United States
Duration: 2022 Jul 102022 Jul 14

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X


Conference59th ACM/IEEE Design Automation Conference, DAC 2022
Country/TerritoryUnited States
CitySan Francisco

Bibliographical note

Funding Information:
ACKNOWLEDGMENTS This work was partly supported by Electronics and Telecommunications Research Institute(ETRI) grant (22ZS1300), the National Research Foundation of Korea(NRF) grant (NRF-2021R1F1A1063262), IITP grant No.2020-0-01361-003 (AI Graduate School-Yonsei Univ.) and 2021-0-02068 (AI Innovation Hub), and Rebellions Inc.

Publisher Copyright:
© 2022 ACM.

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Modelling and Simulation


Dive into the research topics of 'CarM: Hierarchical Episodic Memory for Continual Learning'. Together they form a unique fingerprint.

Cite this