Delgadillo, Itzel C.
Thabet, Ali Kassem
KAUST DepartmentKing Abdullah University of Science and Technology (KAUST), Saudi Arabia
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Visual Computing Center (VCC)
Electrical Engineering Program
Preprint Posting Date2019-11-30
Online Publication Date2020-08-05
Print Publication Date2020-06
Permanent link to this recordhttp://hdl.handle.net/10754/660731
MetadataShow full item record
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.
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
SponsorsThis work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.
Conference/Event name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)