{"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/rethinking-architecture-selection-in-1","title":"Rethinking Architecture Selection in Differentiable NAS","arxiv_id":"2108.04392","date":"2021-08-10","proceeding":"ICLR 2021 1","authors":["Ruochen Wang","Minhao Cheng","Xiangning Chen","Xiaocheng Tang","Cho-Jui Hsieh"],"abstract":"Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly optimizing the model weight and architecture parameters in a weight-sharing supernet via gradient-based algorithms. At the end of the search phase, the operations with the largest architecture parameters will be selected to form the final architecture, with the implicit assumption that the values of architecture parameters reflect the operation strength. While much has been discussed about the supernet's optimization, the architecture selection process has received little attention. We provide empirical and theoretical analysis to show that the magnitude of architecture parameters does not necessarily indicate how much the operation contributes to the supernet's performance. We propose an alternative perturbation-based architecture selection that directly measures each operation's influence on the supernet. We re-evaluate several differentiable NAS methods with the proposed architecture selection and find that it is able to extract significantly improved architectures from the underlying supernets consistently. Furthermore, we find that several failure modes of DARTS can be greatly alleviated with the proposed selection method, indicating that much of the poor generalization observed in DARTS can be attributed to the failure of magnitude-based architecture selection rather than entirely the optimization of its supernet.","url_abs":"https://arxiv.org/abs/2108.04392v1","url_pdf":"https://arxiv.org/pdf/2108.04392v1.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":"rethinking-architecture-selection-in-1","repo_url":"https://github.com/ruocwang/darts-pt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"darts","method_name":"DARTS"},{"method_slug":"differentiable-nas","method_name":"Differentiable NAS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.04392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04392"}},"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/ruocwang/darts-pt","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":"84dd7846a2bf112f","entry":"project_edge","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"84dd7846a2bf112f"}},{"code_sha256_prefix":"ab28014288e5a3fb","entry":"project_op","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab28014288e5a3fb"}},{"code_sha256_prefix":"49fbb02fba2a4916","entry":"count_parameters_in_Compact","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.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":"49fbb02fba2a4916"}},{"code_sha256_prefix":"3e816289579cc9e9","entry":"count_parameters_in_MB","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.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":"3e816289579cc9e9"}},{"code_sha256_prefix":"cb6cc47167b2300d","entry":"distill","repo":"ruocwang/darts-pt","repo_kind":"official","path":"nasbench201/train_search.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/nasbench201/train_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":"cb6cc47167b2300d"}},{"code_sha256_prefix":"75db170ddc22a473","entry":"pt_project","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.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":"75db170ddc22a473"}},{"code_sha256_prefix":"f83bd90cb9018d2d","entry":"save","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.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":"f83bd90cb9018d2d"}},{"code_sha256_prefix":"ccb4bfbd6a962ba5","entry":"save_checkpoint","repo":"ruocwang/darts-pt","repo_kind":"official","path":"sota/cnn/projection.py","file_url":"https://github.com/ruocwang/darts-pt/blob/HEAD/sota/cnn/projection.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":"ccb4bfbd6a962ba5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}