{"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/generic-neural-architecture-search-via","title":"Generic Neural Architecture Search via Regression","arxiv_id":"2108.01899","date":"2021-08-04","proceeding":"NeurIPS 2021 12","authors":["Yuhong Li","Cong Hao","Pan Li","JinJun Xiong","Deming Chen"],"abstract":"Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures, such as ResNet in computer vision and LSTM in natural language processing, are generally good at extracting patterns from the input data and perform well on different downstream tasks. In this paper, we attempt to answer two fundamental questions related to NAS. (1) Is it necessary to use the performance of specific downstream tasks to evaluate and search for good neural architectures? (2) Can we perform NAS effectively and efficiently while being agnostic to the downstream tasks? To answer these questions, we propose a novel and generic NAS framework, termed Generic NAS (GenNAS). GenNAS does not use task-specific labels but instead adopts regression on a set of manually designed synthetic signal bases for architecture evaluation. Such a self-supervised regression task can effectively evaluate the intrinsic power of an architecture to capture and transform the input signal patterns, and allow more sufficient usage of training samples. Extensive experiments across 13 CNN search spaces and one NLP space demonstrate the remarkable efficiency of GenNAS using regression, in terms of both evaluating the neural architectures (quantified by the ranking correlation Spearman's rho between the approximated performances and the downstream task performances) and the convergence speed for training (within a few seconds).","url_abs":"https://arxiv.org/abs/2108.01899v2","url_pdf":"https://arxiv.org/pdf/2108.01899v2.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":"generic-neural-architecture-search-via","repo_url":"https://github.com/leeyeehoo/GenNAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generic-neural-architecture-search-via","repo_url":"https://github.com/leeyeehoo/gennas-zero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-101","task":"Neural Architecture Search","dataset":"NAS-Bench-101","model":"GenNAS","rank_in_archive_order":5,"of":5,"metrics":{"Spearman Correlation":"0.87"},"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":"GenNAS","rank_in_archive_order":15,"of":37,"metrics":{"Accuracy (Test)":"94.18","Accuracy (Val)":"-","Search time (s)":"1080"},"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":"GenNAS","rank_in_archive_order":16,"of":40,"metrics":{"Accuracy (Test)":"72.56","Search time (s)":"1080"},"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":"GenNAS","rank_in_archive_order":24,"of":49,"metrics":{"Accuracy (Test)":"45.59","Search time (s)":"1080"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.01899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01899"}},"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/leeyeehoo/GenNAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leeyeehoo/gennas-zero","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":1,"ran":1,"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":"3763f6adc18d6582","entry":"BarrierNAS","repo":"leeyeehoo/gennas-zero","repo_kind":"listed","path":"model_wrapper/barrier/barrier_nas.py","file_url":"https://github.com/leeyeehoo/gennas-zero/blob/HEAD/model_wrapper/barrier/barrier_nas.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3763f6adc18d6582"}},{"code_sha256_prefix":"7d546663f09e3a88","entry":"trainval","repo":"leeyeehoo/GenNAS","repo_kind":"official","path":"do_search.py","file_url":"https://github.com/leeyeehoo/GenNAS/blob/HEAD/do_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d546663f09e3a88"}},{"code_sha256_prefix":"0e7eabd6dc7a7d54","entry":"trainval","repo":"leeyeehoo/GenNAS","repo_kind":"official","path":"do_sample.py","file_url":"https://github.com/leeyeehoo/GenNAS/blob/HEAD/do_sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e7eabd6dc7a7d54"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}