{"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/semi-supervised-neural-architecture-search","title":"Semi-Supervised Neural Architecture Search","arxiv_id":"2002.10389","date":"2020-02-24","proceeding":"NeurIPS 2020 12","authors":["Renqian Luo","Xu Tan","Rui Wang","Tao Qin","Enhong Chen","Tie-Yan Liu"],"abstract":"Neural architecture search (NAS) relies on a good controller to generate better architectures or predict the accuracy of given architectures. However, training the controller requires both abundant and high-quality pairs of architectures and their accuracy, while it is costly to evaluate an architecture and obtain its accuracy. In this paper, we propose SemiNAS, a semi-supervised NAS approach that leverages numerous unlabeled architectures (without evaluation and thus nearly no cost). Specifically, SemiNAS 1) trains an initial accuracy predictor with a small set of architecture-accuracy data pairs; 2) uses the trained accuracy predictor to predict the accuracy of large amount of architectures (without evaluation); and 3) adds the generated data pairs to the original data to further improve the predictor. The trained accuracy predictor can be applied to various NAS algorithms by predicting the accuracy of candidate architectures for them. SemiNAS has two advantages: 1) It reduces the computational cost under the same accuracy guarantee. On NASBench-101 benchmark dataset, it achieves comparable accuracy with gradient-based method while using only 1/7 architecture-accuracy pairs. 2) It achieves higher accuracy under the same computational cost. It achieves 94.02% test accuracy on NASBench-101, outperforming all the baselines when using the same number of architectures. On ImageNet, it achieves 23.5% top-1 error rate (under 600M FLOPS constraint) using 4 GPU-days for search. We further apply it to LJSpeech text to speech task and it achieves 97% intelligibility rate in the low-resource setting and 15% test error rate in the robustness setting, with 9%, 7% improvements over the baseline respectively.","url_abs":"https://arxiv.org/abs/2002.10389v4","url_pdf":"https://arxiv.org/pdf/2002.10389v4.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":"semi-supervised-neural-architecture-search","repo_url":"https://github.com/renqianluo/SemiNAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semi-supervised-neural-architecture-search","repo_url":"https://github.com/mlvc-lab/Classification-NAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"natural-language-transduction","task_name":"Natural Language Transduction"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"SemiNAS","rank_in_archive_order":83,"of":135,"metrics":{"Accuracy":"76.5","Top-1 Error Rate":"23.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2002.10389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10389"}},"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/mlvc-lab/Classification-NAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/renqianluo/SemiNAS","reach":null}],"summary":{"ran":2,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1},"listed":{"samples":2,"ran":1,"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":"ab3ae1affca959ef","entry":"Attention","repo":"renqianluo/SemiNAS","repo_kind":"official","path":"imagenet/nao_controller.py","file_url":"https://github.com/renqianluo/SemiNAS/blob/HEAD/imagenet/nao_controller.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab3ae1affca959ef"}},{"code_sha256_prefix":"9ac63141be90a73b","entry":"Encoder","repo":"renqianluo/SemiNAS","repo_kind":"official","path":"imagenet/nao_controller.py","file_url":"https://github.com/renqianluo/SemiNAS/blob/HEAD/imagenet/nao_controller.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ac63141be90a73b"}},{"code_sha256_prefix":"83b572d45378f8a3","entry":"move_to_cuda","repo":"mlvc-lab/Classification-NAS","repo_kind":"listed","path":"SemiNAS/nasbench/train_seminas.py","file_url":"https://github.com/mlvc-lab/Classification-NAS/blob/HEAD/SemiNAS/nasbench/train_seminas.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83b572d45378f8a3"}},{"code_sha256_prefix":"8b769fdfd42c56f2","entry":"Decoder","repo":"renqianluo/SemiNAS","repo_kind":"official","path":"imagenet/nao_controller.py","file_url":"https://github.com/renqianluo/SemiNAS/blob/HEAD/imagenet/nao_controller.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b769fdfd42c56f2"}},{"code_sha256_prefix":"998924910b1a7ba5","entry":"NAO","repo":"renqianluo/SemiNAS","repo_kind":"official","path":"imagenet/nao_controller.py","file_url":"https://github.com/renqianluo/SemiNAS/blob/HEAD/imagenet/nao_controller.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"998924910b1a7ba5"}},{"code_sha256_prefix":"e0256c89101161b3","entry":"controller_train","repo":"mlvc-lab/Classification-NAS","repo_kind":"listed","path":"SemiNAS/nasbench/train_seminas.py","file_url":"https://github.com/mlvc-lab/Classification-NAS/blob/HEAD/SemiNAS/nasbench/train_seminas.py","link_basis":"first_harvest_node","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":"e0256c89101161b3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}