Papers › PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search

PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search

28 Apr 2023arXiv:2304.14636links table onlyarchive 2025-07-28

Haibin Wang, Ce Ge, Hesen Chen, Xiuyu Sun

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

The wide application of pre-trained models is driving the trend of once-for-all training in one-shot neural architecture search (NAS). However, training within a huge sample space damages the performance of individual subnets and requires much computation to search for an optimal model. In this paper, we present PreNAS, a search-free NAS approach that accentuates target models in one-shot training. Specifically, the sample space is dramatically reduced in advance by a zero-cost selector, and weight-sharing one-shot training is performed on the preferred architectures to alleviate update conflicts. Extensive experiments have demonstrated that PreNAS consistently outperforms state-of-the-art one-shot NAS competitors for both Vision Transformer and convolutional architectures, and importantly, enables instant specialization with zero search cost. Our code is available at https://github.com/tinyvision/PreNAS.

PaperPDFCodeCode Syntology ranMethod as code

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

Syntology 23 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 3 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 11 ran (10 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 5 ran (5 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.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 16 samples that ran has no recorded date.

tinyvision/prenas officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 11 ran (1 instrument-failed) · 6 unverified report
alibaba/lightweight-neural-architecture-search mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified 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.

Code Syntology ran Syntology

23 samples harvested: 16 ran (of which 3 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 7 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.

1ran · our draft was wrong
15ran
7unverified

Licence: 11 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

tinyvision/prenas official repository 17 samples, 11 ran (1 instrument-failed) · 6 unverified
PatchembedSuper model/supernet_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 5e87d9096209e29f · report fixture: returned PatchembedSuper · level recorded 2026-09-22
ScalingSuper model/supernet_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 026685c04c506554 · report fixture: returned ScalingSuper · level recorded 2026-09-22
SwitchableLayerNormSuper model/supernet_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 19eb86babba84eec · report fixture: returned SwitchableLayerNormSuper · level recorded 2026-09-22
build_transform in 170 papers lib/datasets.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 97eb30cd8a8f60a9 · report fixture: signature is_train:bool/0/bool, args:ArgsConfig/0/? · returned Compose · level recorded 2026-09-25
candidate_to_choices candidates_to_choices.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 33be0fe904fcd4bb · report fixture: signature candidate_path:str/0/str, topN:float/0/float · returned dict · level recorded 2026-09-25
decode_cand_tuple evolution_pre_train.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · b328ce4411979624 · report fixture: signature cand_tuple:tuple/1/int · returned tuple · level recorded, date not recorded
gen_key lib/score_maker.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 3c63fe350b1181ce · report fixture: signature embed_dim:int/0/int, choice:str/0/str · returned str · level recorded 2026-09-25
get_max_min_model evolution_pre_train.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 59df9b4c9ddc23e1 · report fixture: signature choices:dict/0/? · returned tuple · level recorded 2026-09-26
sample_a_cand supernet_engine.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 3b90681597c539f9 · report fixture: signature candidates:list/1/str, grouping:list/1/list, exclude:list/1/int · returned str · level recorded 2026-09-26
sample_a_config supernet_engine.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · bc914e97a3d6f3c5 · report fixture: signature choices:dict/0/?, efunc:callable/0/? · returned dict · level recorded 2026-09-25
sample_candidates supernet_engine.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e74419e5b0847287 · report fixture: signature candidates:list/1/dict, eval:bool/0/bool, sandwich:int/0/int, sandwich_base:bool/0/bool, sandwich_top:bool/0/bool, shuffle:bool/0/bool, grouping:list/1/list · returned dict · level recorded 2026-09-25
AttentionSuper model/supernet_transformer.py unverified Apache-2.0 (permissive) · 707554979346fab5 · report
TransformerEncoderLayer in 90 papers model/supernet_transformer.py unverified Apache-2.0 (permissive) · a17eb310e7b4dff6 · report
Vision_TransformerSuper model/supernet_transformer.py unverified Apache-2.0 (permissive) · f1400f07fc9772f7 · report
build_dataset in 151 papers lib/datasets.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · afa7efdfbea334df · report
is_master in 43 papers lib/score_maker.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 9680c55c004e3572 · report
unwrap_model in 41 papers lib/score_maker.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 2bf62c0287050bdd · report
alibaba/lightweight-neural-architecture-search community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
func_receive_dict_inputs modelscope/utils/file_utils.py ran Apache-2.0 (permissive) · 6f8b42ebbb59d908 · report fixture: signature func:callable/0/? · returned bool · level recorded 2026-09-25
has_method modelscope/utils/import_utils.py ran Apache-2.0 (permissive) · ecaa7193a5bfc39e · report fixture: signature obj:SimpleObject/0/?, method:str/0/str · returned bool · level recorded 2026-09-26
import_modules_from_file modelscope/utils/import_utils.py ran Apache-2.0 (permissive) · 2eeb911987d072eb · report fixture: signature py_file:str/0/str · returned tuple · level recorded 2026-09-25
is_method_overridden modelscope/utils/import_utils.py ran Apache-2.0 (permissive) · f22f6715f6935b8b · report fixture: signature method:str/0/str, base_class:callable/0/?, derived_class:callable/0/? · returned bool · level recorded 2026-09-26
read_file in 112 papers modelscope/utils/file_utils.py ran Apache-2.0 (permissive) · 0531c04dd4901504 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-25
get_logger in 383 papers modelscope/utils/logger.py unverified Apache-2.0 (permissive) · 21b93c8efc0f5b5c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for PreNAS (graph method: PreNAS). 19 bricks; individually on a fixture: 15 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Vision_TransformerSuper entry · level 0 · unverified · f1400f07fc9772f7
  2. LayerNormSuper helper · level 0 · unverified · e4f3e6207e219ef8
  3. LinearSuper model · level 1 · ran · 46ae2d4f3fc0bdd6
  4. PatchembedSuper helper · level 1 · ran · 5e87d9096209e29f
  5. ScalingSuper helper · level 1 · ran · 026685c04c506554
  6. SwitchableLayerNormSuper helper · level 1 · ran · 19eb86babba84eec
  7. TransformerEncoderLayer model · level 0 · unverified · a17eb310e7b4dff6
  8. calc_dropout helper · level 1 · ran · honoured contract · 72a860a9aff50105
  9. trunc_normal_ helper · level 1 · ran; the contract check could not run · 605878f6dcef72e9
  10. sample_bias helper · level 1 · ran · our draft was wrong · 963bc33b77cf8148
  11. sample_weight helper · level 1 · ran · our draft was wrong · 1d3488a4b38ea75d
  12. AttentionSuper model · level 0 · unverified · 707554979346fab5
  13. DropPath helper · level 1 · ran · 691dde70dfd8362b
  14. drop_path helper · level 1 · ran; the contract check could not run · 39eace7e2822504f
  15. gelu helper · level 1 · ran · honoured contract · 08a5be1ffa0676e3
  16. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 813ed3a96c17cf42
  17. RelativePosition2D_super helper · level 1 · ran · 701ac4868b3a9368
  18. qkv_super model · level 1 · ran · c356588a20cf831d
  19. _ntuple helper · level 1 · ran · our draft was wrong · e2c1a7dffcdbe918

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2304.14636") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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