Show simple item record

dc.contributor.authorLi, Guohao
dc.contributor.authorQian, Guocheng
dc.contributor.authorDelgadillo, Itzel C.
dc.contributor.authorMüller, Matthias
dc.contributor.authorThabet, Ali Kassem
dc.contributor.authorGhanem, Bernard
dc.date.accessioned2019-12-22T12:55:20Z
dc.date.available2019-12-22T12:55:20Z
dc.date.issued2020-08-05
dc.identifier.citationLi, G., Qian, G., Delgadillo, I. C., Muller, M., Thabet, A., & Ghanem, B. (2020). SGAS: Sequential Greedy Architecture Search. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00169
dc.identifier.isbn978-1-7281-7169-2
dc.identifier.issn1063-6919
dc.identifier.doi10.1109/CVPR42600.2020.00169
dc.identifier.urihttp://hdl.handle.net/10754/660731
dc.description.abstractArchitecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, discovered architectures often fail to generalize in the final evaluation. Architectures with a higher validation accuracy during the search phase may perform worse in the evaluation. Aiming to alleviate this common issue, we introduce sequential greedy architecture search (SGAS), an efficient method for neural architecture search. By dividing the search procedure into sub-problems, SGAS chooses and prunes candidate operations in a greedy fashion. We apply SGAS to search architectures for Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN). Extensive experiments show that SGAS is able to find state-of-the-art architectures for tasks such as image classification, point cloud classification and node classification in protein-protein interaction graphs with minimal computational cost.
dc.description.sponsorshipThis work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9157406/
dc.relation.urlhttps://ieeexplore.ieee.org/document/9157406/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9157406
dc.rightsArchived with thanks to IEEE
dc.titleSGAS: Sequential Greedy Architecture Search
dc.typeConference Paper
dc.contributor.departmentKing Abdullah University of Science and Technology (KAUST), Saudi Arabia
dc.contributor.departmentComputer Science
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentElectrical Engineering Program
dc.conference.date13-19 June 2020
dc.conference.name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.locationSeattle, WA, USA
dc.eprint.versionPost-print
dc.contributor.institutionIntelligent Systems Lab, Intel Labs, Germany
dc.identifier.arxivid1912.00195
kaust.personLi, Guohao
kaust.personQian, Guocheng
kaust.personDelgadillo, Itzel C.
kaust.personThabet, Ali Kassem
kaust.personGhanem, Bernard
refterms.dateFOA2019-12-22T12:55:55Z
kaust.acknowledged.supportUnitOffice of Sponsored Research
kaust.acknowledged.supportUnitVisual Computing Center (VCC)
dc.date.published-online2020-08-05
dc.date.published-print2020-06
dc.date.posted2019-11-30


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
670.6Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record