{"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/mixpath-a-unified-approach-for-one-shot","title":"MixPath: A Unified Approach for One-shot Neural Architecture Search","arxiv_id":"2001.05887","date":"2020-01-16","proceeding":"ICCV 2023 1","authors":["Xiangxiang Chu","Shun Lu","Xudong Li","Bo Zhang"],"abstract":"Blending multiple convolutional kernels is proved advantageous in neural architecture design. However, current two-stage neural architecture search methods are mainly limited to single-path search spaces. How to efficiently search models of multi-path structures remains a difficult problem. In this paper, we are motivated to train a one-shot multi-path supernet to accurately evaluate the candidate architectures. Specifically, we discover that in the studied search spaces, feature vectors summed from multiple paths are nearly multiples of those from a single path. Such disparity perturbs the supernet training and its ranking ability. Therefore, we propose a novel mechanism called Shadow Batch Normalization (SBN) to regularize the disparate feature statistics. Extensive experiments prove that SBNs are capable of stabilizing the optimization and improving ranking performance. We call our unified multi-path one-shot approach as MixPath, which generates a series of models that achieve state-of-the-art results on ImageNet.","url_abs":"https://arxiv.org/abs/2001.05887v4","url_pdf":"https://arxiv.org/pdf/2001.05887v4.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":"mixpath-a-unified-approach-for-one-shot","repo_url":"https://github.com/xiaomi-automl/MixPath","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"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":"https://syntology.ai/paper/2001.05887","atlas_url":"https://app.syntology.ai/?focus=2001.05887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05887"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaomi-automl/MixPath","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"bcd04c37b18b6139","entry":"validate","repo":"xiaomi-automl/MixPath","repo_kind":"official","path":"S1/train_search.py","file_url":"https://github.com/xiaomi-automl/MixPath/blob/HEAD/S1/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bcd04c37b18b6139"}},{"code_sha256_prefix":"bc160d8be9b08be0","entry":"validate","repo":"xiaomi-automl/MixPath","repo_kind":"official","path":"NasBench101/nas_train_search.py","file_url":"https://github.com/xiaomi-automl/MixPath/blob/HEAD/NasBench101/nas_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc160d8be9b08be0"}},{"code_sha256_prefix":"60067ef302d62a21","entry":"validate_cali","repo":"xiaomi-automl/MixPath","repo_kind":"official","path":"NasBench101/nas_train_search.py","file_url":"https://github.com/xiaomi-automl/MixPath/blob/HEAD/NasBench101/nas_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60067ef302d62a21"}},{"code_sha256_prefix":"47f49406e8ae052c","entry":"validate_search","repo":"xiaomi-automl/MixPath","repo_kind":"official","path":"NasBench101/nas_train_search.py","file_url":"https://github.com/xiaomi-automl/MixPath/blob/HEAD/NasBench101/nas_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47f49406e8ae052c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}