Papers › Understanding Architectures Learnt by Cell-based Neural Architecture Search

Understanding Architectures Learnt by Cell-based Neural Architecture Search

20 Sep 2019ICLR 2020 1arXiv:1909.09569archive 2025-07-28

Yao Shu, Wei Wang, Shaofeng Cai

Neural architecture search (NAS) searches architectures automatically for given tasks, e.g., image classification and language modeling. Improving the search efficiency and effectiveness have attracted increasing attention in recent years. However, few efforts have been devoted to understanding the generated architectures. In this paper, we first reveal that existing NAS algorithms (e.g., DARTS, ENAS) tend to favor architectures with wide and shallow cell structures. These favorable architectures consistently achieve fast convergence and are consequently selected by NAS algorithms. Our empirical and theoretical study further confirms that their fast convergence derives from their smooth loss landscape and accurate gradient information. Nonetheless, these architectures may not necessarily lead to better generalization performance compared with other candidate architectures in the same search space, and therefore further improvement is possible by revising existing NAS algorithms.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

shuyao95/Understanding-NAS officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationLanguage ModelingLanguage ModellingNeural Architecture Searchimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DARTS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections