{"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/deeper-insights-into-weight-sharing-in-neural-1","title":"Deeper Insights into Weight Sharing in Neural Architecture Search","arxiv_id":"2001.01431","date":"2020-01-06","proceeding":null,"authors":["Yuge Zhang","Zejun Lin","Junyang Jiang","Quanlu Zhang","Yujing Wang","Hui Xue","Chen Zhang","Yaming Yang"],"abstract":"With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention. As training every child model from scratch is very time-consuming, recent works leverage weight-sharing to speed up the model evaluation procedure. These approaches greatly reduce computation by maintaining a single copy of weights on the super-net and share the weights among every child model. However, weight-sharing has no theoretical guarantee and its impact has not been well studied before. In this paper, we conduct comprehensive experiments to reveal the impact of weight-sharing: (1) The best-performing models from different runs or even from consecutive epochs within the same run have significant variance; (2) Even with high variance, we can extract valuable information from training the super-net with shared weights; (3) The interference between child models is a main factor that induces high variance; (4) Properly reducing the degree of weight sharing could effectively reduce variance and improve performance.","url_abs":"https://arxiv.org/abs/2001.01431v1","url_pdf":"https://arxiv.org/pdf/2001.01431v1.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":"deeper-insights-into-weight-sharing-in-neural-1","repo_url":"https://github.com/ultmaster/deeper-insights-weight-sharing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"speed","method_name":"SPEED"},{"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/2001.01431","atlas_url":"https://app.syntology.ai/?focus=2001.01431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01431"}},"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/ultmaster/deeper-insights-weight-sharing","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"fcde1a98c0385d78","entry":"config_uglify","repo":"ultmaster/deeper-insights-weight-sharing","repo_kind":"official","path":"submit_utils.py","file_url":"https://github.com/ultmaster/deeper-insights-weight-sharing/blob/HEAD/submit_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcde1a98c0385d78"}},{"code_sha256_prefix":"1d6c0c0dff1c1274","entry":"data_transforms","repo":"ultmaster/deeper-insights-weight-sharing","repo_kind":"official","path":"preproc.py","file_url":"https://github.com/ultmaster/deeper-insights-weight-sharing/blob/HEAD/preproc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d6c0c0dff1c1274"}},{"code_sha256_prefix":"bf0bc305c2302fec","entry":"get_parser","repo":"ultmaster/deeper-insights-weight-sharing","repo_kind":"official","path":"config.py","file_url":"https://github.com/ultmaster/deeper-insights-weight-sharing/blob/HEAD/config.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf0bc305c2302fec"}},{"code_sha256_prefix":"7ac97563dbd4f579","entry":"parse","repo":"ultmaster/deeper-insights-weight-sharing","repo_kind":"official","path":"genotypes.py","file_url":"https://github.com/ultmaster/deeper-insights-weight-sharing/blob/HEAD/genotypes.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ac97563dbd4f579"}},{"code_sha256_prefix":"654a527a9f7f0bc9","entry":"drop_path_","repo":"ultmaster/deeper-insights-weight-sharing","repo_kind":"official","path":"models/ops.py","file_url":"https://github.com/ultmaster/deeper-insights-weight-sharing/blob/HEAD/models/ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"654a527a9f7f0bc9"}},{"code_sha256_prefix":"eb9857d523d512dc","entry":"from_str","repo":"ultmaster/deeper-insights-weight-sharing","repo_kind":"official","path":"genotypes.py","file_url":"https://github.com/ultmaster/deeper-insights-weight-sharing/blob/HEAD/genotypes.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb9857d523d512dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}