Papers › Learning Where To Look -- Generative NAS is Surprisingly Efficient

Learning Where To Look -- Generative NAS is Surprisingly Efficient

16 Mar 2022arXiv:2203.08734archive 2025-07-28

Jovita Lukasik, Steffen Jung, Margret Keuper

The efficient, automated search for well-performing neural architectures (NAS) has drawn increasing attention in the recent past. Thereby, the predominant research objective is to reduce the necessity of costly evaluations of neural architectures while efficiently exploring large search spaces. To this aim, surrogate models embed architectures in a latent space and predict their performance, while generative models for neural architectures enable optimization-based search within the latent space the generator draws from. Both, surrogate and generative models, have the aim of facilitating query-efficient search in a well-structured latent space. In this paper, we further improve the trade-off between query-efficiency and promising architecture generation by leveraging advantages from both, efficient surrogate models and generative design. To this end, we propose a generative model, paired with a surrogate predictor, that iteratively learns to generate samples from increasingly promising latent subspaces. This approach leads to very effective and efficient architecture search, while keeping the query amount low. In addition, our approach allows in a straightforward manner to jointly optimize for multiple objectives such as accuracy and hardware latency. We show the benefit of this approach not only w.r.t. the optimization of architectures for highest classification accuracy but also in the context of hardware constraints and outperform state-of-the-art methods on several NAS benchmarks for single and multiple objectives. We also achieve state-of-the-art performance on ImageNet. The code is available at http://github.com/jovitalukasik/AG-Net .

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 15 code samples harvested from 1 repository linked to this paper: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 8 ran (6 with no instrument failure; 2 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jovitalukasik/AG-Net officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 8 ran (2 instrument-failed) · 7 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

15 samples harvested: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 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
1ran; the contract check could not run
6ran
7unverified

Licence: 0 of the 15 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 jovitalukasik/AG-Net. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

jovitalukasik/AG-Net official repository 15 samples, 8 ran (2 instrument-failed) · 7 unverified
Embedding_Network Generator.py ran fingerprinted MIT (permissive) · 582d38d6fe781c5d · report fixture: returned Embedding_Network · level recorded 2026-09-22
GraphAggr Generator.py ran MIT (permissive) · ce4b703f0ca4ac1d · report fixture: returned GraphAggr · level recorded 2026-09-22
MLP_predictor Generator.py ran fingerprinted MIT (permissive) · 6108502415b404b5 · report fixture: returned MLP_predictor · level recorded 2026-09-22
NodeAdd Generator.py ran MIT (permissive) · 2b9fe11164cf5625 · report fixture: returned NodeAdd · level recorded 2026-09-22
NodeInit Generator.py ran MIT (permissive) · dad4798b4ede036f · report fixture: returned NodeInit · level recorded 2026-09-22
Nodes Generator.py ran MIT (permissive) · 775bc58aa0b13b2c · report fixture: signature h:Tensor/3/float, h_v:Tensor/2/float, h_G:Tensor/2/float, c:Tensor/2/float · returned Tensor · level recorded 2026-09-24
adj_to_scores Generator.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 79e9ac44d05a5e89 · report fixture: signature adj:Tensor/2/float, l:int/0/int · returned Tensor · level recorded 2026-09-22
scores_to_adj Generator.py ran · our draft was wrong MIT (permissive) · 07bfd504987b0c00 · report fixture: signature scores:Tensor/1/float, num_nodes:int/0/int · returned Tensor · level recorded 2026-09-22
GNNDecoder Generator.py unverified MIT (permissive) · 7a4c97aeb50377dc · report
GNNLayer_backward Generator.py unverified MIT (permissive) · 2d556bf1eff82766 · report
GNNLayer_forward Generator.py unverified MIT (permissive) · 010094ca34994468 · report
Generator in 95 papers Generator.py unverified MIT (permissive) · 011cde17ef45ee9a · report
Generator_Decoder Generator.py unverified MIT (permissive) · 5d7d83be99daf869 · report
GraphEmbed Generator.py unverified MIT (permissive) · 57beeabace709277 · report
NodeEmbUpd Generator.py unverified MIT (permissive) · bfe2ce35559e1337 · 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 generative model with surrogate predictor (graph method: generative model with surrogate predictor). 15 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. Generator_Decoder entry · level 0 · unverified · 5d7d83be99daf869
  2. GNNDecoder model · level 0 · unverified · 7a4c97aeb50377dc
  3. MLP_predictor helper · level 1 · ran · 6108502415b404b5
  4. adj_to_scores helper · level 1 · ran; the contract check could not run (RAISES) · 79e9ac44d05a5e89
  5. scores_to_adj helper · level 1 · ran · our draft was wrong · 07bfd504987b0c00
  6. Generator model · level 0 · unverified · 011cde17ef45ee9a
  7. GraphEmbed model · level 0 · unverified · 57beeabace709277
  8. NodeAdd helper · level 1 · ran · 2b9fe11164cf5625
  9. NodeInit helper · level 1 · ran · dad4798b4ede036f
  10. Nodes helper · level 1 · ran · 775bc58aa0b13b2c
  11. GraphAggr helper · level 1 · ran · ce4b703f0ca4ac1d
  12. NodeEmbUpd model · level 0 · unverified · bfe2ce35559e1337
  13. Embedding_Network helper · level 1 · ran · 582d38d6fe781c5d
  14. GNNLayer_backward helper · level 0 · unverified · 2d556bf1eff82766
  15. GNNLayer_forward helper · level 0 · unverified · 010094ca34994468

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="2203.08734") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Neural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search NAS-Bench-201, CIFAR-10 AG-Net Accuracy (Test) 94.37 #3 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 AG-Net Accuracy (Val) 91.61 #3 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 AG-Net Accuracy (Test) 73.51 #5 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 AG-Net Accuracy (Val) 73.49 #5 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 AG-Net Accuracy (Test) 46.42 #7 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 AG-Net Accuracy (Val) 46.73 #7 of 49 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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