Papers › Multi-conditioned Graph Diffusion for Neural Architecture Search

Multi-conditioned Graph Diffusion for Neural Architecture Search

9 Mar 2024arXiv:2403.06020archive 2025-07-28

Rohan Asthana, Joschua Conrad, Youssef Dawoud, Maurits Ortmanns, Vasileios Belagiannis

Neural architecture search automates the design of neural network architectures usually by exploring a large and thus complex architecture search space. To advance the architecture search, we present a graph diffusion-based NAS approach that uses discrete conditional graph diffusion processes to generate high-performing neural network architectures. We then propose a multi-conditioned classifier-free guidance approach applied to graph diffusion networks to jointly impose constraints such as high accuracy and low hardware latency. Unlike the related work, our method is completely differentiable and requires only a single model training. In our evaluations, we show promising results on six standard benchmarks, yielding novel and unique architectures at a fast speed, i.e. less than 0.2 seconds per architecture. Furthermore, we demonstrate the generalisability and efficiency of our method through experiments on ImageNet dataset.

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="2403.06020")

Code

Syntology Ran 4 of 7 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

rohanasthana/dinas officialmentioned in paperpytorchMIT 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

7 samples harvested; 4 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.

1ran · our draft was wrong
1ran · fixture could not drive it
2ran
3unverified

Licence: 0 of the 7 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 rohanasthana/dinas. “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.

adj_to_scores rohanasthana/dinas/src/Generator.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 79e9ac44d05a5e89 · report
scores_to_adj rohanasthana/dinas/src/Generator.py official repository ran · our draft was wrong MIT (permissive) · 07bfd504987b0c00 · report
setup_wandb rohanasthana/dinas/main_reg_free.py official repository ran MIT (permissive) · cb06d97097718c4f · report
sort_edge_index rohanasthana/dinas/src/NASBench301_self.py official repository ran fingerprinted MIT (permissive) · 5f3d687c7190555d · report
files_exist rohanasthana/dinas/src/generate_samples.py official repository unverified MIT (permissive) · ba546bbe7d90467a · report
laplacian_positional_encoding rohanasthana/dinas/src/generate_samples.py official repository unverified MIT (permissive) · c4e9ad9f0df2e0c3 · report
to_list rohanasthana/dinas/src/generate_samples.py official repository unverified MIT (permissive) · 85832bcd5531c861 · report

Tasks

Neural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search NAS-Bench-101 DiNAS Accuracy (%) 94.98% #1 of 5 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DiNAS Accuracy (Test) 94.37 #1 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DiNAS Accuracy (Val) 91.61 #1 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DiNAS Search time (s) 15.36 #1 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DiNAS Accuracy (Test) 73.51 #1 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DiNAS Accuracy (Val) 73.49 #1 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DiNAS Search time (s) 15.36 #1 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 DiNAS Accuracy (Test) 45.41 #27 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 DiNAS Accuracy (Val) 46.66 #27 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 DiNAS Search time (s) 15.36 #27 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-301 DiNAS Accuracy (Val) 94.92 #1 of 1 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.

Methods

Diffusion

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