Papers › Surprisingly Strong Performance Prediction with Neural Graph Features

Surprisingly Strong Performance Prediction with Neural Graph Features

25 Apr 2024arXiv:2404.16551archive 2025-07-28

Gabriela Kadlecová, Jovita Lukasik, Martin Pilát, Petra Vidnerová, Mahmoud Safari, Roman Neruda, Frank Hutter

Performance prediction has been a key part of the neural architecture search (NAS) process, allowing to speed up NAS algorithms by avoiding resource-consuming network training. Although many performance predictors correlate well with ground truth performance, they require training data in the form of trained networks. Recently, zero-cost proxies have been proposed as an efficient method to estimate network performance without any training. However, they are still poorly understood, exhibit biases with network properties, and their performance is limited. Inspired by the drawbacks of zero-cost proxies, we propose neural graph features (GRAF), simple to compute properties of architectural graphs. GRAF offers fast and interpretable performance prediction while outperforming zero-cost proxies and other common encodings. In combination with other zero-cost proxies, GRAF outperforms most existing performance predictors at a fraction of the cost.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.16551")

Code

Syntology Ran 19 of 22 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 19 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 19 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gabikadlecova/zc_combine officialmentioned in paperMIT 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

22 samples harvested; 19 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

19ran
3unverified

Licence: 0 of the 22 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 gabikadlecova/zc_combine. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

aggregate_isomorphic_scores gabikadlecova/zc_combine/zc_combine/fixes/utils.py official repository ran MIT (permissive) · a0cd5cb2d67c483f · report
apply_layer_dropout_relu gabikadlecova/zc_combine/zc_combine/predictors/gnn.py official repository ran MIT (permissive) · 8f09f06ced25bf21 · report
compute_feature_df gabikadlecova/zc_combine/zc_combine/features/dataset.py official repository ran MIT (permissive) · 076a7b43b581f744 · report
count_edges gabikadlecova/zc_combine/zc_combine/features/nasbench101.py official repository ran MIT (permissive) · feee61f724f4fe31 · report
count_ops gabikadlecova/zc_combine/zc_combine/features/base.py official repository ran MIT (permissive) · fc531b68e3daae1c · report
count_ops_opnodes gabikadlecova/zc_combine/zc_combine/features/base.py official repository ran MIT (permissive) · 820f496e1ce6d0c5 · report
count_switches gabikadlecova/zc_combine/zc_combine/features/tnb101_macro.py official repository ran MIT (permissive) · 4074afd5d8f8712e · report
edge gabikadlecova/zc_combine/zc_combine/fixes/utils.py official repository ran MIT (permissive) · da5ba5a4db691671 · report
filter_by_range gabikadlecova/zc_combine/zc_combine/fixes/operations.py official repository ran MIT (permissive) · 72ce8a466cc40e81 · report
get_state_at_i gabikadlecova/zc_combine/zc_combine/features/tnb101_macro.py official repository ran MIT (permissive) · 38fba84176f9db88 · report
load_from_config gabikadlecova/zc_combine/zc_combine/features/dataset.py official repository ran MIT (permissive) · 9a4c1d594afc3573 · report
log_dataset_args gabikadlecova/zc_combine/zc_combine/utils/args_utils.py official repository ran MIT (permissive) · 83112c2bbada9b2c · report
op_on_pos gabikadlecova/zc_combine/zc_combine/features/nasbench201.py official repository ran MIT (permissive) · 19f379c601ea9e9f · report
parse_and_read_args gabikadlecova/zc_combine/zc_combine/utils/args_utils.py official repository ran MIT (permissive) · 7d6da07092b48621 · report
parse_ops_nb201 gabikadlecova/zc_combine/zc_combine/fixes/operations.py official repository ran MIT (permissive) · 963aae00115ab847 · report
parse_ops_nb301 gabikadlecova/zc_combine/zc_combine/fixes/operations.py official repository ran MIT (permissive) · c79827e617a35632 · report
remap_values gabikadlecova/zc_combine/zc_combine/features/conversions.py official repository ran fingerprinted MIT (permissive) · da732986788c2dc3 · report
to_graph gabikadlecova/zc_combine/zc_combine/features/base.py official repository ran MIT (permissive) · 73cae9b8d56e5f84 · report
zero_outgoing gabikadlecova/zc_combine/zc_combine/fixes/utils.py official repository ran MIT (permissive) · fd21b29f71363669 · report
get_feature_dataset gabikadlecova/zc_combine/zc_combine/features/dataset.py official repository unverified MIT (permissive) · 6a2d7c76fc5717cd · report
to_dataset gabikadlecova/zc_combine/zc_combine/predictors/gnn.py official repository unverified MIT (permissive) · 2c6ead1f8f01739f · report
train gabikadlecova/zc_combine/zc_combine/predictors/gnn.py official repository unverified MIT (permissive) · 21314b00e73896ce · report

Tasks

Neural Architecture SearchPrediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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