Papers › HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning

HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning

16 Jun 2021arXiv:2106.08630archive 2025-07-28

Hayeon Lee, Sewoong Lee, Song Chong, Sung Ju Hwang

For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on hardware-aware NAS collect a large number of samples (e.g., accuracy and latency) from a target device, either builds a lookup table or a latency estimator. However, such approach is impractical in real-world scenarios as there exist numerous devices with different hardware specifications, and collecting samples from such a large number of devices will require prohibitive computational and monetary cost. To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples. To this end, we introduce novel hardware embeddings to embed any devices considering them as black-box functions that output latencies, and meta-learn the hardware-adaptive latency predictor in a device-dependent manner, using the hardware embeddings. We validate the proposed HELP for its latency estimation performance on unseen platforms, on which it achieves high estimation performance with as few as 10 measurement samples, outperforming all relevant baselines. We also validate end-to-end NAS frameworks using HELP against ones without it, and show that it largely reduces the total time cost of the base NAS method, in latency-constrained settings. Code is available at https://github.com/HayeonLee/HELP.

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 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 17 samples from 1 repository, 14 ran (14 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hayeonlee/help officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 14 ran (0 instrument-failed) · 3 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

17 samples harvested: 14 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 3 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 · honoured contract
13ran
3unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 hayeonlee/help. “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 1 sample 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.

hayeonlee/help official repository 17 samples, 14 ran (0 instrument-failed) · 3 unverified
GCN in 41 papers help.py ran MIT (permissive) · 71fc6adbc8a9e344 · report fixture: returned GCN · level recorded 2026-09-22
GraphConvolution in 36 papers help.py ran MIT (permissive) · c39b18210d6af850 · report fixture: returned GraphConvolution · level recorded 2026-09-22
InferenceNetwork help.py ran MIT (permissive) · 96fdfe319609dfb1 · report fixture: returned InferenceNetwork · level recorded 2026-09-22
Net in 54 papers help.py ran MIT (permissive) · 91e2f33eece76754 · report fixture: returned Net · level recorded 2026-09-22
build_activation in 5 papers ofa/utils/pytorch_modules.py ran MIT (permissive) · da7205ae31eaf8ba · report fixture: signature act_func:str/0/str, inplace:bool/0/bool · returned ReLU · level recorded 2026-09-25
build_val_transform validate_imagenet.py ran MIT (permissive) here; the stored copy is pointer only · e1ccc3331db22b7d · report fixture: signature size:int/0/int · returned Compose · level recorded 2026-09-24
flat in 11 papers utils.py ran MIT (permissive) · 1d5210b89b90aa66 · report fixture: signature v:Tensor/2/float · returned ndarray · level recorded 2026-09-25
get_bn_param ofa/utils/my_modules.py ran MIT (permissive) · f060e6240188a921 · report fixture: signature net:callable/0/? · returned dict · level recorded 2026-09-25
get_minmax_latency_index utils.py ran MIT (permissive) · 1cf245a941c1244c · report fixture: signature meta_train_devices:list/1/str, train_idx:dict/0/?, latency:dict/0/? · returned tuple · level recorded 2026-09-25
kl_diagnormal_stdnormal help.py ran · honoured contract MIT (permissive) · e268490969567b33 · report fixture: signature p:Normal/0/? · returned Tensor · level recorded 2026-09-22
log_prob in 9 papers utils.py ran MIT (permissive) · 9b55ec99f8807af5 · report fixture: signature dist:Normal/0/?, groundtruth:Tensor/2/float · returned Tensor · level recorded 2026-09-25
make_divisible in 76 papers ofa/utils/pytorch_modules.py ran MIT (permissive) · addfbda3077115a3 · report fixture: signature v:int/0/int, divisor:int/0/int, min_val:NoneType/0/? · returned int · level recorded 2026-09-25
str2bool in 533 papers parser.py ran MIT (permissive) · b0717d29ccfec107 · report fixture: signature v:str/0/str · returned bool · level recorded 2026-09-25
str2list in 12 papers parser.py ran fingerprinted MIT (permissive) · 8ce900951a7ddd54 · report fixture: signature v:list/1/str · returned list · level recorded 2026-09-25
Data in 7 papers help.py unverified MIT (permissive) · d3c44d4cc08c514e · report
HELP help.py unverified MIT (permissive) · dd8282187a60fb88 · report
MetaLearner in 5 papers help.py unverified MIT (permissive) · ef8967f45af71fa1 · 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 HELP (graph method: HELP). 8 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. HELP entry · level 0 · unverified · dd8282187a60fb88
  2. Data helper · level 0 · unverified · d3c44d4cc08c514e
  3. InferenceNetwork helper · level 1 · ran · 96fdfe319609dfb1
  4. MetaLearner helper · level 0 · unverified · ef8967f45af71fa1
  5. kl_diagnormal_stdnormal helper · level 1 · ran · honoured contract · e268490969567b33
  6. GCN helper · level 1 · ran · 71fc6adbc8a9e344
  7. Net helper · level 1 · ran · 91e2f33eece76754
  8. GraphConvolution helper · level 1 · ran · c39b18210d6af850

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="2106.08630") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Meta-LearningNeural Architecture Search

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