Papers › NAS-Bench-101: Towards Reproducible Neural Architecture Search

NAS-Bench-101: Towards Reproducible Neural Architecture Search

25 Feb 2019arXiv:1902.09635archive 2025-07-28

Chris Ying, Aaron Klein, Esteban Real, Eric Christiansen, Kevin Murphy, Frank Hutter

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the pre-computed dataset. We demonstrate its utility by analyzing the dataset as a whole and by benchmarking a range of architecture optimization algorithms.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repositories (google-research/nasbench, automl/nas_benchmarks) is linked to this paper; the 10 samples below come from 1 community repository. Syntology harvested code from google-research/nasbench for another paper; from automl/nas_benchmarks for another paper.

google-research/nasbench: Syntology's graph links these samples to Interpretable Neural Architecture Search via Bayesian Optimisation with... (arXiv:2006.07556; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. automl/nas_benchmarks: Syntology's graph links these samples to Interpretable Neural Architecture Search via Bayesian Optimisation with... (arXiv:2006.07556; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 10 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/nasbench officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Interpretable Neural Architecture Search via Bayesian Optimisation with... (arXiv:2006.07556; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
automl/nas_benchmarks officialmentioned in paperBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Interpretable Neural Architecture Search via Bayesian Optimisation with... (arXiv:2006.07556; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
DaveKim3872/nasbench-hpc mentioned on GitHubtfApache-2.0Syntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report
eric-vader/HD-BO-Additive-Models mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces (arXiv:1902.03229; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
1unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from DaveKim3872/nasbench-hpc. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

DaveKim3872/nasbench-hpc community (archive-listed) 10 samples, 9 ran (0 instrument-failed) · 1 unverified
gen_is_edge_fn nasbench/lib/graph_util.py ran Apache-2.0 (permissive) · b558868dfd1955d6 · report fixture: signature bits:int/0/int · returned vectorize · level recorded 2026-09-24
is_full_dag nasbench/lib/graph_util.py ran fingerprinted Apache-2.0 (permissive) · 283b1ed886dfa4c1 · report fixture: signature matrix:ndarray/2/int · returned bool · level recorded 2026-09-24
is_included delete_redundancy.py ran Apache-2.0 (permissive) · 4e196702d29923e4 · report fixture: signature item:dict/0/?, item_list:list/1/dict · returned bool · level recorded 2026-09-24
is_included delete_with_step.py ran Apache-2.0 (permissive) · 18f8dd429732fc7a · report fixture: signature item:dict/0/?, item_list:list/1/dict · returned int · level recorded 2026-09-24
is_upper_triangular nasbench/lib/model_spec.py ran fingerprinted Apache-2.0 (permissive) · de7246ef524e6189 · report fixture: signature matrix:ndarray/2/float · returned bool · level recorded 2026-09-24
matrix_eq_comp delete_redundancy.py ran Apache-2.0 (permissive) · 8912b1df700ddccb · report fixture: signature mat1:ndarray/1/int, mat2:ndarray/1/int · returned int64 · level recorded 2026-09-24
num_edges nasbench/lib/graph_util.py ran Apache-2.0 (permissive) · 2e655699a68fae2a · report fixture: signature matrix:ndarray/2/int · returned int64 · level recorded 2026-09-24
one_dif delete_redundancy.py ran Apache-2.0 (permissive) · 8cbe0e9bb117c4c8 · report fixture: signature item0:dict/0/?, item1:dict/0/? · returned bool · level recorded 2026-09-24
one_dif delete_with_step.py ran Apache-2.0 (permissive) · ef1f44ad9b01eddd · report fixture: signature item0:dict/0/?, item1:dict/0/? · returned bool · level recorded 2026-09-24
conv_bn_relu in 20 papers nasbench/lib/base_ops.py unverified Apache-2.0 (permissive) · 1500e49c46a26813 · report

Tasks

BenchmarkingNeural Architecture Search

Datasets

Introduced by this paper, per the archive.

NAS-Bench-101

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections