research-article

CarM: hierarchical episodic memory for continual learning

Authors:

Minindu Weerakoon,

Myeongjae JeonAuthors Info & Claims

DAC '22: Proceedings of the 59th ACM/IEEE Design Automation Conference

Pages 1147 - 1152

https://doi.org/10.1145/3489517.3530587

Published: 23 August 2022 Publication History

Abstract

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.

References

[1]

Rahaf Aljundi, Min Lin, Baptiste Goujaud, and Yoshua Bengio. 2019. Gradient Based Sample Selection for Online Continual Learning. In NeurIPS.

[2]

Jihwan Bang, Heesu Kim, YoungJoon Yoo, Jung-Woo Ha, and Jonghyun Choi. 2021. Rainbow Memory: Continual Learning with a Memory of Diverse Samples. In CVPR.

[3]

Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, and SIMONE CALDERARA. 2020. Dark Experience for General Continual Learning: a Strong, Simple Baseline. In NeurIPS.

[4]

Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Cordelia Schmid, and Karteek Alahari. 2018. End-to-End Incremental Learning. In ECCV.

[5]

Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan, and Philip H. S. Torr. 2018. Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. In ECCV.

[6]

Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, and Mohamed Elhoseiny. 2019. Efficient Lifelong Learning with A-GEM. In ICLR.

[7]

Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K Dokania, Philip HS Torr, and Marc'Aurelio Ranzato. 2019. On Tiny Episodic Memories in Continual Learning. arXiv:1902.10486 (2019).

[8]

Aristotelis Chrysakis and Marie-Francine Moens. 2020. Online Continual Learning from Imbalanced Data. In ICML.

[9]

Enrico Fini, Stéphane Lathuilière, Enver Sangineto, Moin Nabi, and Elisa Ricci. 2020. Online Continual Learning under Extreme Memory Constraints. In ECCV.

[10]

Alexander Gepperth and Barbara Hammer. 2016. Incremental Learning Algorithms and Applications. In ESANN.

[11]

Xisen Jin, Junyi Du, and Xiang Ren. 2020. Gradient Based Memory Editing for Task-Free Continual Learning. arXiv:2006.15294 (2020).

[12]

James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. 2017. Overcoming Catastrophic Forgetting in Neural Networks. In PNAS.

[13]

Zhizhong Li and Derek Hoiem. 2017. Learning without Forgetting. In IEEE Trans. PAMI.

[14]

David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient Episodic Memory for Continual Learning. In NeurIPS.

[15]

M. McCloskey and Neal. 1989. Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem. In Psychology of Learning and Motivation.

[16]

Ameya Prabhu, Philip HS Torr, and Puneet K Dokania. 2020. GDumb: A Simple Approach that Questions Our Progress in Continual Learning. In ECCV.

[17]

Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H. Lampert. 2017. iCaRL: Incremental Classifier and Representation Learning. In CVPR.

[18]

Dongsub Shim, Zheda Mai, Jihwan Jeong, Scott Sanner, Hyunwoo Kim, and Jongseong Jang. 2021. Online Class-Incremental Continual Learning with Adversarial Shapley Value. In AAAI.

[19]

Gido M van de Ven and Andreas S Tolias. 2018. Three Continual Learning Scenarios and a Case for Generative Replay. In NeurIPS Workshop on Continual Learning.

[20]

Jeffrey S Vitter. 1985. Random Sampling with a Reservoir. In ACM TOMS.

[21]

Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Fu. 2019. Large Scale Incremental Learning. In CVPR.

[22]

Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual Learning Through Synaptic Intelligence. In ICML.

Cited By

Zhu SVoigt TRahimian FKo J(2024)On-device Training: A First Overview on Existing SystemsACM Transactions on Sensor Networks10.1145/369600320:6(1-39)Online publication date: 14-Sep-2024
https://dl.acm.org/doi/10.1145/3696003
Gong CZheng ZWu FJia XChen GGanesan DLane NShi W(2024)Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual LearningProceedings of the 30th Annual International Conference on Mobile Computing and Networking10.1145/3636534.3690701(1408-1423)Online publication date: 4-Dec-2024
https://dl.acm.org/doi/10.1145/3636534.3690701
Zhu JDu CGuo D(2024)Target-Aspect Domain Continual SAR-ATR Based on Task Hard Attention MechanismIEEE Geoscience and Remote Sensing Letters10.1109/LGRS.2024.344928921(1-5)Online publication date: 2024
https://doi.org/10.1109/LGRS.2024.3449289
Show More Cited By

Recommendations

WOM-Code Solutions for Low Latency and High Endurance in Phase Change Memory
This paper describes a write-once-memory-code phase change memory (WOM-code PCM) architecture for next-generation non-volatile memory applications. Specifically, we address the long latency of the write operation in PCM—attributed to PCM SET—...
A Novel Memory Block Management Scheme for PCM Using WOM-Code
HPCC-CSS-ICESS '15: Proceedings of the 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conf on Embedded Software and Systems

Phase Change Memory (PCM) is a promising DRAM replacement in embedded systems due to its attractive characteristics including low static power consumption and high density. However, long write latency is one of the major drawbacks in current PCM ...
Mellow writes: extending lifetime in resistive memories through selective slow write backs
ISCA'16

Emerging resistive memory technologies, such as PCRAM and ReRAM, have been proposed as promising replacements for DRAM-based main memory, due to their better scalability, low standby power, and non-volatility. However, limited write endurance is a major ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

DAC '22: Proceedings of the 59th ACM/IEEE Design Automation Conference

July 2022

1462 pages

ISBN:9781450391429

DOI:10.1145/3489517

General Chair:
Rob Oshana
NXP

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGDA: ACM Special Interest Group on Design Automation
IEEE CEDA

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 23 August 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article

Funding Sources

IITP
Rebellions Inc.
Electronics and Telecommunications Research Institute (ETRI)
National Research Foundation of Korea (NRF)

Conference

DAC '22

Sponsor:

SIGDA

DAC '22: 59th ACM/IEEE Design Automation Conference

July 10 - 14, 2022

California, San Francisco

Acceptance Rates

Overall Acceptance Rate 1,770 of 5,499 submissions, 32%

Upcoming Conference

DAC '25

Sponsor:
sigda

62nd ACM/IEEE Design Automation Conference

June 22 - 26, 2025

San Francisco , CA , USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
211
Total Downloads

Downloads (Last 12 months)105
Downloads (Last 6 weeks)8

Reflects downloads up to 03 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zhu SVoigt TRahimian FKo J(2024)On-device Training: A First Overview on Existing SystemsACM Transactions on Sensor Networks10.1145/369600320:6(1-39)Online publication date: 14-Sep-2024
https://dl.acm.org/doi/10.1145/3696003
Gong CZheng ZWu FJia XChen GGanesan DLane NShi W(2024)Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual LearningProceedings of the 30th Annual International Conference on Mobile Computing and Networking10.1145/3636534.3690701(1408-1423)Online publication date: 4-Dec-2024
https://dl.acm.org/doi/10.1145/3636534.3690701
Zhu JDu CGuo D(2024)Target-Aspect Domain Continual SAR-ATR Based on Task Hard Attention MechanismIEEE Geoscience and Remote Sensing Letters10.1109/LGRS.2024.344928921(1-5)Online publication date: 2024
https://doi.org/10.1109/LGRS.2024.3449289
Kim YOh CHwang JKim WOh SLee YSharma HYazdanbakhsh APark J(2024)DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)10.1109/ISCA59077.2024.00093(1246-1261)Online publication date: 29-Jun-2024
https://doi.org/10.1109/ISCA59077.2024.00093
Khan VCygert SDeja KTrzcinski TTwardowski B(2024)Looking Through the Past: Better Knowledge Retention for Generative Replay in Continual LearningIEEE Access10.1109/ACCESS.2024.337914812(45309-45317)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3379148
Horsuwan TLertvittayakumjorn PKanwatchara KKijsirikul BVateekul P(2024)Meta Lifelong-Learning With Selective and Task-Aware AdaptationIEEE Access10.1109/ACCESS.2024.336566312(34099-34115)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3365663
Ma XJeong SZhang MWang DChoi JJeon MCosta XAl Hassanieh HAsadi ACox LPerino DWidmer JGiustiniano D(2023)Cost-effective On-device Continual Learning over Memory Hierarchy with MiroProceedings of the 29th Annual International Conference on Mobile Computing and Networking10.1145/3570361.3613297(1-15)Online publication date: 2-Oct-2023
https://dl.acm.org/doi/10.1145/3570361.3613297
Yu XDong FRen HZhang CZou LZhou Y(2023)Multilevel Adaptive Knowledge Distillation Network for Incremental SAR Target RecognitionIEEE Geoscience and Remote Sensing Letters10.1109/LGRS.2023.326365920(1-5)Online publication date: 2023
https://doi.org/10.1109/LGRS.2023.3263659
Min QHe JYu PFu Y(2023)Incremental Fault Diagnosis Method Based on Metric Feature Distillation and Improved Sample MemoryIEEE Access10.1109/ACCESS.2023.327448111(46015-46025)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3274481

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents