{"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/shapley-nas-discovering-operation-1","title":"Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search","arxiv_id":"2206.09811","date":"2022-06-20","proceeding":"CVPR 2022 1","authors":["Han Xiao","Ziwei Wang","Zheng Zhu","Jie zhou","Jiwen Lu"],"abstract":"In this paper, we propose a Shapley value based method to evaluate operation contribution (Shapley-NAS) for neural architecture search. Differentiable architecture search (DARTS) acquires the optimal architectures by optimizing the architecture parameters with gradient descent, which significantly reduces the search cost. However, the magnitude of architecture parameters updated by gradient descent fails to reveal the actual operation importance to the task performance and therefore harms the effectiveness of obtained architectures. By contrast, we propose to evaluate the direct influence of operations on validation accuracy. To deal with the complex relationships between supernet components, we leverage Shapley value to quantify their marginal contributions by considering all possible combinations. Specifically, we iteratively optimize the supernet weights and update the architecture parameters by evaluating operation contributions via Shapley value, so that the optimal architectures are derived by selecting the operations that contribute significantly to the tasks. Since the exact computation of Shapley value is NP-hard, the Monte-Carlo sampling based algorithm with early truncation is employed for efficient approximation, and the momentum update mechanism is adopted to alleviate fluctuation of the sampling process. Extensive experiments on various datasets and various search spaces show that our Shapley-NAS outperforms the state-of-the-art methods by a considerable margin with light search cost. The code is available at https://github.com/Euphoria16/Shapley-NAS.git","url_abs":"https://arxiv.org/abs/2206.09811v1","url_pdf":"https://arxiv.org/pdf/2206.09811v1.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":"shapley-nas-discovering-operation-1","repo_url":"https://github.com/euphoria16/shapley-nas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"Shapley-NAS(best)","rank_in_archive_order":14,"of":41,"metrics":{"Parameters":"3.6M","Top-1 Error Rate":"2.43%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"Shapley-NAS","rank_in_archive_order":92,"of":135,"metrics":{"MACs":"582M","Params":"5.4M","Top-1 Error Rate":"23.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-10","model":"Shapley-NAS","rank_in_archive_order":2,"of":37,"metrics":{"Accuracy (Test)":"94.37","Accuracy (Val)":"91.61"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"Shapley-NAS","rank_in_archive_order":3,"of":40,"metrics":{"Accuracy (Test)":"73.51","Accuracy (Val)":"73.49"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"Shapley-NAS","rank_in_archive_order":2,"of":49,"metrics":{"Accuracy (Test)":"46.85","Accuracy (Val)":"46.57"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.09811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09811"}},"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/euphoria16/shapley-nas","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Euphoria16/Shapley-NAS","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"40f63134baaceef0","entry":"Cell","repo":"Euphoria16/Shapley-NAS","repo_kind":"official","path":"model_search.py","file_url":"https://github.com/Euphoria16/Shapley-NAS/blob/HEAD/model_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"40f63134baaceef0"}},{"code_sha256_prefix":"b08dc05a407456d6","entry":"MixedOp","repo":"Euphoria16/Shapley-NAS","repo_kind":"official","path":"model_search.py","file_url":"https://github.com/Euphoria16/Shapley-NAS/blob/HEAD/model_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b08dc05a407456d6"}},{"code_sha256_prefix":"9e15b2a3585f7e27","entry":"Network","repo":"Euphoria16/Shapley-NAS","repo_kind":"official","path":"model_search.py","file_url":"https://github.com/Euphoria16/Shapley-NAS/blob/HEAD/model_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e15b2a3585f7e27"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}