{"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/attentivenas-improving-neural-architecture","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","arxiv_id":"2011.09011","date":"2020-11-18","proceeding":"CVPR 2021 1","authors":["Dilin Wang","Meng Li","Chengyue Gong","Vikas Chandra"],"abstract":"Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves remarkable search efficiency and accuracy. Two-stage NAS requires sampling from the search space during training, which directly impacts the accuracy of the final searched models. While uniform sampling has been widely used for its simplicity, it is agnostic of the model performance Pareto front, which is the main focus in the search process, and thus, misses opportunities to further improve the model accuracy. In this work, we propose AttentiveNAS that focuses on improving the sampling strategy to achieve better performance Pareto. We also propose algorithms to efficiently and effectively identify the networks on the Pareto during training. Without extra re-training or post-processing, we can simultaneously obtain a large number of networks across a wide range of FLOPs. Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77.3% to 80.7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks. We also achieve ImageNet accuracy of 80.1% with only 491 MFLOPs. Our training code and pretrained models are available at https://github.com/facebookresearch/AttentiveNAS.","url_abs":"https://arxiv.org/abs/2011.09011v2","url_pdf":"https://arxiv.org/pdf/2011.09011v2.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":"attentivenas-improving-neural-architecture","repo_url":"https://github.com/facebookresearch/AttentiveNAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attentivenas-improving-neural-architecture","repo_url":"https://github.com/facebookresearch/AlphaNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"neural-architecture-search","method_name":"Neural Architecture Search"},{"method_slug":"ppo","method_name":"PPO"},{"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":[{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"AttentiveNAS-A5","rank_in_archive_order":22,"of":135,"metrics":{"Accuracy":"80.1","MACs":"491M","Top-1 Error Rate":"19.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"AttentiveNAS-A4","rank_in_archive_order":25,"of":135,"metrics":{"Accuracy":"79.8","MACs":"444M","Top-1 Error Rate":"20.2"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"AttentiveNAS-A3","rank_in_archive_order":36,"of":135,"metrics":{"Accuracy":"79.1","MACs":"357M","Top-1 Error Rate":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"AttentiveNAS-A2","rank_in_archive_order":42,"of":135,"metrics":{"Accuracy":"78.8","MACs":"317M","Top-1 Error Rate":"21.2"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"AttentiveNAS-A1","rank_in_archive_order":48,"of":135,"metrics":{"Accuracy":"78.4","MACs":"279M","Top-1 Error Rate":"21.6"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"AttentiveNAS-A0","rank_in_archive_order":66,"of":135,"metrics":{"Accuracy":"77.3","MACs":"203M","Top-1 Error Rate":"22.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.09011","atlas_url":"https://app.syntology.ai/?focus=2011.09011","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":"2011.09011"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2011.09011\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2011.09011"},"call":"get_concepts_for_paper(arxiv_id=\"2011.09011\")"}],"by_repo":[{"repo":"facebookresearch/AttentiveNAS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2102.07954"],"harvested_for_calls":[{"arxiv_id":"2102.07954","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.07954"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.07954\")"}]},{"repo":"facebookresearch/AlphaNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2102.07954"],"harvested_for_calls":[{"arxiv_id":"2102.07954","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.07954"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.07954\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"c2edd24282741d5bc767999349be5c6041b91535311deadbd19bb6f112771182","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}