{"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/neural-architecture-search-with-gbdt","title":"Accuracy Prediction with Non-neural Model for Neural Architecture Search","arxiv_id":"2007.04785","date":"2020-07-09","proceeding":null,"authors":["Renqian Luo","Xu Tan","Rui Wang","Tao Qin","Enhong Chen","Tie-Yan Liu"],"abstract":"Neural architecture search (NAS) with an accuracy predictor that predicts the accuracy of candidate architectures has drawn increasing attention due to its simplicity and effectiveness. Previous works usually employ neural network-based predictors which require more delicate design and are easy to overfit. Considering that most architectures are represented as sequences of discrete symbols which are more like tabular data and preferred by non-neural predictors, in this paper, we study an alternative approach which uses non-neural model for accuracy prediction. Specifically, as decision tree based models can better handle tabular data, we leverage gradient boosting decision tree (GBDT) as the predictor for NAS. We demonstrate that the GBDT predictor can achieve comparable (if not better) prediction accuracy than neural network based predictors. Moreover, considering that a compact search space can ease the search process, we propose to prune the search space gradually according to important features derived from GBDT. In this way, NAS can be performed by first pruning the search space and then searching a neural architecture, which is more efficient and effective. Experiments on NASBench-101 and ImageNet demonstrate the effectiveness of using GBDT as predictor for NAS: (1) On NASBench-101, it is 22x, 8x, and 6x more sample efficient than random search, regularized evolution, and Monte Carlo Tree Search (MCTS) in finding the global optimum; (2) It achieves 24.2% top-1 error rate on ImageNet, and further achieves 23.4% top-1 error rate on ImageNet when enhanced with search space pruning. Code is provided at https://github.com/renqianluo/GBDT-NAS.","url_abs":"https://arxiv.org/abs/2007.04785v3","url_pdf":"https://arxiv.org/pdf/2007.04785v3.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":"neural-architecture-search-with-gbdt","repo_url":"https://github.com/renqianluo/GBDT-NAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"shap","method_name":"SHAP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"GBDT-NAS-3S","rank_in_archive_order":81,"of":135,"metrics":{"Accuracy":"76.5","MACs":"577M","Params":"6.4M","Top-1 Error Rate":"23.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.04785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.04785"}},"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/renqianluo/GBDT-NAS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"469bf48752905889","entry":"accuracy","repo":"renqianluo/GBDT-NAS","repo_kind":"official","path":"imagenet/utils.py","file_url":"https://github.com/renqianluo/GBDT-NAS/blob/HEAD/imagenet/utils.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":"469bf48752905889"}},{"code_sha256_prefix":"7652dde45ec300c3","entry":"convert_arch_to_seq","repo":"renqianluo/GBDT-NAS","repo_kind":"official","path":"nasbench/utils.py","file_url":"https://github.com/renqianluo/GBDT-NAS/blob/HEAD/nasbench/utils.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":"7652dde45ec300c3"}},{"code_sha256_prefix":"07179da1319d3649","entry":"item","repo":"renqianluo/GBDT-NAS","repo_kind":"official","path":"imagenet/utils.py","file_url":"https://github.com/renqianluo/GBDT-NAS/blob/HEAD/imagenet/utils.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":"07179da1319d3649"}},{"code_sha256_prefix":"a3f52c5753448b8d","entry":"move_to_cuda","repo":"renqianluo/GBDT-NAS","repo_kind":"official","path":"imagenet/utils.py","file_url":"https://github.com/renqianluo/GBDT-NAS/blob/HEAD/imagenet/utils.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":"a3f52c5753448b8d"}},{"code_sha256_prefix":"b67a23c671fb776b","entry":"profile","repo":"renqianluo/GBDT-NAS","repo_kind":"official","path":"imagenet/measure.py","file_url":"https://github.com/renqianluo/GBDT-NAS/blob/HEAD/imagenet/measure.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":"b67a23c671fb776b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}