{"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/eat-nas-elastic-architecture-transfer-for","title":"EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search","arxiv_id":"1901.05884","date":"2019-01-17","proceeding":null,"authors":["Jiemin Fang","Yukang Chen","Xinbang Zhang","Qian Zhang","Chang Huang","Gaofeng Meng","Wenyu Liu","Xinggang Wang"],"abstract":"Neural architecture search (NAS) methods have been proposed to release human\nexperts from tedious architecture engineering. However, most current methods\nare constrained in small-scale search due to the issue of computational\nresources. Meanwhile, directly applying architectures searched on small\ndatasets to large datasets often bears no performance guarantee. This\nlimitation impedes the wide use of NAS on large-scale tasks. To overcome this\nobstacle, we propose an elastic architecture transfer mechanism for\naccelerating large-scale neural architecture search (EAT-NAS). In our\nimplementations, architectures are first searched on a small dataset, e.g.,\nCIFAR-10. The best one is chosen as the basic architecture. The search process\non the large dataset, e.g., ImageNet, is initialized with the basic\narchitecture as the seed. The large-scale search process is accelerated with\nthe help of the basic architecture. What we propose is not only a NAS method\nbut a mechanism for architecture-level transfer.\n  In our experiments, we obtain two final models EATNet-A and EATNet-B that\nachieve competitive accuracies, 74.7% and 74.2% on ImageNet, respectively,\nwhich also surpass the models searched from scratch on ImageNet under the same\nsettings. For the computational cost, EAT-NAS takes only less than 5 days on 8\nTITAN X GPUs, which is significantly less than the computational consumption of\nthe state-of-the-art large-scale NAS methods.","url_abs":"http://arxiv.org/abs/1901.05884v3","url_pdf":"http://arxiv.org/pdf/1901.05884v3.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":"eat-nas-elastic-architecture-transfer-for","repo_url":"https://github.com/JaminFong/EAT-NAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.05884"}},"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/JaminFong/EAT-NAS","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"0d21b442d12afbf7","entry":"get_eatnet_param","repo":"JaminFong/EAT-NAS","repo_kind":"official","path":"symbol_eatnas_search.py","file_url":"https://github.com/JaminFong/EAT-NAS/blob/HEAD/symbol_eatnas_search.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":"0d21b442d12afbf7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}