{"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/unchain-the-search-space-with-hierarchical","title":"Unchain the Search Space with Hierarchical Differentiable Architecture Search","arxiv_id":"2101.04028","date":"2021-01-11","proceeding":null,"authors":["Guanting Liu","Yujie Zhong","Sheng Guo","Matthew R. Scott","Weilin Huang"],"abstract":"Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly focus on searching for a repeatable cell structure, which is then stacked sequentially in multiple stages to form the networks. This configuration significantly reduces the search space, and ignores the importance of connections between the cells. To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level. Specifically, the cell-level search space is relaxed so that the networks can learn stage-specific cell structures. For the stage-level search, we systematically study the architectures of stages, including the number of cells in each stage and the connections between the cells. Based on insightful observations, we design several search rules and losses, and mange to search for better stage-level architectures. Such hierarchical search space greatly improves the performance of the networks without introducing expensive search cost. Extensive experiments on CIFAR10 and ImageNet demonstrate the effectiveness of the proposed H-DAS. Moreover, the searched stage-level architectures can be combined with the cell structures searched by existing DAS methods to further boost the performance. Code is available at: https://github.com/MalongTech/research-HDAS","url_abs":"https://arxiv.org/abs/2101.04028v2","url_pdf":"https://arxiv.org/pdf/2101.04028v2.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":"unchain-the-search-space-with-hierarchical","repo_url":"https://github.com/MalongTech/research-hdas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.04028","atlas_url":"https://app.syntology.ai/?focus=2101.04028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.04028"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/msight-tech/research-HDAS","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"found_in_text":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"c145b4b1d1132a1d","entry":"parse","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c145b4b1d1132a1d"}},{"code_sha256_prefix":"694c959c84a05011","entry":"GetCell","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"694c959c84a05011"}},{"code_sha256_prefix":"1bbcd36c15f8091c","entry":"SearchBigDAG","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1bbcd36c15f8091c"}},{"code_sha256_prefix":"d0c97492871096d5","entry":"SearchStage","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d0c97492871096d5"}},{"code_sha256_prefix":"760f269d932f4c22","entry":"SearchStageController","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"760f269d932f4c22"}},{"code_sha256_prefix":"fdfb2f691ca67d7f","entry":"broadcast_list","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fdfb2f691ca67d7f"}},{"code_sha256_prefix":"ecbba95fa148c004","entry":"to_dag","repo":"msight-tech/research-HDAS","repo_kind":"found_in_text","path":"models/search_stage.py","file_url":"https://github.com/msight-tech/research-HDAS/blob/HEAD/models/search_stage.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ecbba95fa148c004"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}