{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/one-shot-neural-architecture-search-via-self","title":"One-Shot Neural Architecture Search via Self-Evaluated Template Network","arxiv_id":"1910.05733","date":"2019-10-13","proceeding":"ICCV 2019 10","authors":["Xuanyi Dong","Yi Yang"],"abstract":"Neural architecture search (NAS) aims to automate the search procedure of architecture instead of manual design. Even if recent NAS approaches finish the search within days, lengthy training is still required for a specific architecture candidate to get the parameters for its accurate evaluation. Recently one-shot NAS methods are proposed to largely squeeze the tedious training process by sharing parameters across candidates. In this way, the parameters for each candidate can be directly extracted from the shared parameters instead of training them from scratch. However, they have no sense of which candidate will perform better until evaluation so that the candidates to evaluate are randomly sampled and the top-1 candidate is considered the best. In this paper, we propose a Self-Evaluated Template Network (SETN) to improve the quality of the architecture candidates for evaluation so that it is more likely to cover competitive candidates. SETN consists of two components: (1) an evaluator, which learns to indicate the probability of each individual architecture being likely to have a lower validation loss. The candidates for evaluation can thus be selectively sampled according to this evaluator. (2) a template network, which shares parameters among all candidates to amortize the training cost of generated candidates. In experiments, the architecture found by SETN achieves state-of-the-art performance on CIFAR and ImageNet benchmarks within comparable computation costs. Code is publicly available on GitHub: https://github.com/D-X-Y/AutoDL-Projects.","url_abs":"https://arxiv.org/abs/1910.05733v4","url_pdf":"https://arxiv.org/pdf/1910.05733v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"one-shot-neural-architecture-search-via-self","repo_url":"https://github.com/D-X-Y/AutoDL-Projects","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-shot-neural-architecture-search-via-self","repo_url":"https://github.com/D-X-Y/NAS-Projects","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-shot-neural-architecture-search-via-self","repo_url":"https://github.com/D-X-Y/GDAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-shot-neural-architecture-search-via-self","repo_url":"https://github.com/xxlya/COS598D_Assignment1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"SETN (T=1K) + CutOut","rank_in_archive_order":30,"of":41,"metrics":{"Search Time (GPU days)":"1.8","Top-1 Error Rate":"2.69%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"SETN","rank_in_archive_order":34,"of":40,"metrics":{"Accuracy (Test)":"56.87","Accuracy (Val)":"59.05","Search time (s)":"31010"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"SETN","rank_in_archive_order":49,"of":49,"metrics":{"Accuracy (Val)":"32.52"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.05733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05733"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/D-X-Y/AutoDL-Projects","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xxlya/COS598D_Assignment1","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/D-X-Y/GDAS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/D-X-Y/NAS-Projects","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"490b5c41400816e1","entry":"backward_step_unrolled","repo":"D-X-Y/GDAS","repo_kind":"listed","path":"exps/NAS-Bench-201-algos/DARTS-V2.py","file_url":"https://github.com/D-X-Y/GDAS/blob/HEAD/exps/NAS-Bench-201-algos/DARTS-V2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"490b5c41400816e1"}},{"code_sha256_prefix":"c9db316e18458ccd","entry":"mutate_arch_func","repo":"D-X-Y/GDAS","repo_kind":"listed","path":"exps/NAS-Bench-201-algos/R_EA.py","file_url":"https://github.com/D-X-Y/GDAS/blob/HEAD/exps/NAS-Bench-201-algos/R_EA.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9db316e18458ccd"}},{"code_sha256_prefix":"1ab9fd355247f264","entry":"train_and_eval","repo":"D-X-Y/GDAS","repo_kind":"listed","path":"exps/NAS-Bench-201-algos/R_EA.py","file_url":"https://github.com/D-X-Y/GDAS/blob/HEAD/exps/NAS-Bench-201-algos/R_EA.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ab9fd355247f264"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}