XST: A Crossbar Column-wise Sparse Training for Efficient Continual Learning

Fan Zhang, Li Yang, Jian Meng, Jae Sun Seo, Yu Cao, Deliang Fan

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

3 Scopus citations

Abstract

Leveraging the ReRAM crossbar-based In-Memory-Computing (IMC) to accelerate single task DNN inference has been widely studied. However, using the ReRAM crossbar for continual learning has not been explored yet. In this work, we propose XST, a novel crossbar column-wise sparse training framework for continual learning. XST significantly reduces the training cost and saves inference energy. More importantly, it is friendly to existing crossbar-based convolution engine with almost no hardware overhead. Compared with the state-of-the-art CPG method, the experiments show that XST's accuracy achieves 4.95 % higher accuracy. Furthermore, XST demonstrates 5.59 × training speedup and 1.5 × inference energy-saving.

Original languageEnglish (US)
Title of host publicationProceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022
EditorsCristiana Bolchini, Ingrid Verbauwhede, Ioana Vatajelu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages48-51
Number of pages4
ISBN (Electronic)9783981926361
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 - Virtual, Online, Belgium
Duration: Mar 14 2022Mar 23 2022

Publication series

NameProceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022

Conference

Conference2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022
Country/TerritoryBelgium
CityVirtual, Online
Period3/14/223/23/22

Bibliographical note

Publisher Copyright:
© 2022 EDAA.

Keywords

  • Continual Learning
  • In-Memory-Computing
  • Sparse Learning

Fingerprint

Dive into the research topics of 'XST: A Crossbar Column-wise Sparse Training for Efficient Continual Learning'. Together they form a unique fingerprint.

Cite this