{"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/fairnas-rethinking-evaluation-fairness-of","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","arxiv_id":"1907.01845","date":"2019-07-03","proceeding":"ICCV 2021 10","authors":["Xiangxiang Chu","Bo Zhang","Ruijun Xu"],"abstract":"One of the most critical problems in weight-sharing neural architecture search is the evaluation of candidate models within a predefined search space. In practice, a one-shot supernet is trained to serve as an evaluator. A faithful ranking certainly leads to more accurate searching results. However, current methods are prone to making misjudgments. In this paper, we prove that their biased evaluation is due to inherent unfairness in the supernet training. In view of this, we propose two levels of constraints: expectation fairness and strict fairness. Particularly, strict fairness ensures equal optimization opportunities for all choice blocks throughout the training, which neither overestimates nor underestimates their capacity. We demonstrate that this is crucial for improving the confidence of models' ranking. Incorporating the one-shot supernet trained under the proposed fairness constraints with a multi-objective evolutionary search algorithm, we obtain various state-of-the-art models, e.g., FairNAS-A attains 77.5% top-1 validation accuracy on ImageNet. The models and their evaluation codes are made publicly available online http://github.com/fairnas/FairNAS .","url_abs":"https://arxiv.org/abs/1907.01845v5","url_pdf":"https://arxiv.org/pdf/1907.01845v5.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":"fairnas-rethinking-evaluation-fairness-of","repo_url":"https://github.com/fairnas/FairNAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fairnas-rethinking-evaluation-fairness-of","repo_url":"https://github.com/xiaomi-automl/FairNAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"image-classification","task_name":"Image Classification"},{"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":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FairNAS-A","rank_in_archive_order":951,"of":1060,"metrics":{"GFLOPs":"0.776","Number of params":"4.6M","Top 1 Accuracy":"75.34%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FairNAS-B","rank_in_archive_order":959,"of":1060,"metrics":{"GFLOPs":"0.690","Number of params":"4.5M","Top 1 Accuracy":"75.10%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"FairNAS-C","rank_in_archive_order":973,"of":1060,"metrics":{"GFLOPs":"0.642","Number of params":"4.4M","Top 1 Accuracy":"74.69%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"FairNAS-A","rank_in_archive_order":3,"of":41,"metrics":{"FLOPS":"391","Parameters":"3","Search Time (GPU days)":"8","Top-1 Error Rate":"1.8%"},"uses_additional_data":true},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"FairNAS-A","rank_in_archive_order":110,"of":135,"metrics":{"Accuracy":"75.34","MACs":"388M","Params":"4.6M","Top-1 Error Rate":"24.7"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"FairNAS-B","rank_in_archive_order":114,"of":135,"metrics":{"Accuracy":"75.1","MACs":"345M","Params":"4.5M","Top-1 Error Rate":"24.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"FairNAS-C","rank_in_archive_order":119,"of":135,"metrics":{"Accuracy":"74.69","MACs":"321M","Params":"4.4M","Top-1 Error Rate":"25.4"},"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":"FairNAS","rank_in_archive_order":25,"of":37,"metrics":{"Accuracy (Test)":"93.23","Accuracy (Val)":"90.07","Search time (s)":"9845"},"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":"FairNAS","rank_in_archive_order":24,"of":40,"metrics":{"Accuracy (Test)":"71.00","Accuracy (Val)":"70.94","Search time (s)":"9845"},"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":"FairNAS","rank_in_archive_order":32,"of":49,"metrics":{"Accuracy (Test)":"42.19","Search time (s)":"9845"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-1","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, CIFAR-10","model":"FairNAS (Chu et al., 2021)","rank_in_archive_order":7,"of":11,"metrics":{"Test Accuracy":"93.23"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-2","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, CIFAR-100","model":"FairNAS (Chu et al., 2021)","rank_in_archive_order":7,"of":11,"metrics":{"Test Accuracy":"71.00"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, ImageNet16-120","model":"FairNAS (Chu et al., 2021)","rank_in_archive_order":7,"of":11,"metrics":{"Test Accuracy":"42.19"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.01845","atlas_url":"https://app.syntology.ai/?focus=1907.01845","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":"1907.01845"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1907.01845\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1907.01845"},"call":"get_concepts_for_paper(arxiv_id=\"1907.01845\")"}],"by_repo":[{"repo":"fairnas/FairNAS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xiaomi-automl/FairNAS","kind":"listed","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":"5bdcfbf3acd0fd96e4fe015f5219b1fd14668ce67b0677b3a6960159cad438e4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}