{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/b-darts-beta-decay-regularization-for","title":"$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search","arxiv_id":"2203.01665","date":"2022-03-03","proceeding":null,"authors":["Peng Ye","Baopu Li","Yikang Li","Tao Chen","Jiayuan Fan","Wanli Ouyang"],"abstract":"Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficiency. However, they suffer from two main issues, the weak robustness to the performance collapse and the poor generalization ability of the searched architectures. To solve these two problems, a simple-but-efficient regularization method, termed as Beta-Decay, is proposed to regularize the DARTS-based NAS searching process. Specifically, Beta-Decay regularization can impose constraints to keep the value and variance of activated architecture parameters from too large. Furthermore, we provide in-depth theoretical analysis on how it works and why it works. Experimental results on NAS-Bench-201 show that our proposed method can help to stabilize the searching process and makes the searched network more transferable across different datasets. In addition, our search scheme shows an outstanding property of being less dependent on training time and data. Comprehensive experiments on a variety of search spaces and datasets validate the effectiveness of the proposed method.","url_abs":"https://arxiv.org/abs/2203.01665v2","url_pdf":"https://arxiv.org/pdf/2203.01665v2.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":"b-darts-beta-decay-regularization-for","repo_url":"https://github.com/Sunshine-Ye/Beta-DARTS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"darts","method_name":"DARTS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"β-DARTS","rank_in_archive_order":23,"of":41,"metrics":{"Top-1 Error Rate":"2.53%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-100-1","task":"Neural Architecture Search","dataset":"CIFAR-100","model":"β-DARTS","rank_in_archive_order":8,"of":13,"metrics":{"Percentage Error":"16.52"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"b-DARTS (CIFAR-10)","rank_in_archive_order":93,"of":135,"metrics":{"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":"β-DARTS","rank_in_archive_order":4,"of":37,"metrics":{"Accuracy (Test)":"94.36","Accuracy (Val)":"91.55"},"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":"β-DARTS","rank_in_archive_order":2,"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":"β-SDARTS-RS","rank_in_archive_order":3,"of":49,"metrics":{"Accuracy (Test)":"46.71"},"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":"β-RDARTS-L2","rank_in_archive_order":4,"of":49,"metrics":{"Accuracy (Test)":"46.71"},"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":"β-DARTS","rank_in_archive_order":12,"of":49,"metrics":{"Accuracy (Test)":"46.34","Accuracy (Val)":"46.37"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.01665","atlas_url":"https://app.syntology.ai/?focus=2203.01665","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.01665"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.01665\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.01665"},"call":"get_concepts_for_paper(arxiv_id=\"2203.01665\")"}],"by_repo":[{"repo":"Sunshine-Ye/Beta-DARTS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d875d7109a6fc7a335d7c131ee1510b1fe1e264aa4da6cd9f6af5d1d4b8cde8d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}