Papers › DARTS-: Robustly Stepping out of Performance Collapse Without Indicators

DARTS-: Robustly Stepping out of Performance Collapse Without Indicators

2 Sep 2020ICLR 2021 1arXiv:2009.01027archive 2025-07-28

Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, Junchi Yan

Despite the fast development of differentiable architecture search (DARTS), it suffers from long-standing performance instability, which extremely limits its application. Existing robustifying methods draw clues from the resulting deteriorated behavior instead of finding out its causing factor. Various indicators such as Hessian eigenvalues are proposed as a signal to stop searching before the performance collapses. However, these indicator-based methods tend to easily reject good architectures if the thresholds are inappropriately set, let alone the searching is intrinsically noisy. In this paper, we undertake a more subtle and direct approach to resolve the collapse. We first demonstrate that skip connections have a clear advantage over other candidate operations, where it can easily recover from a disadvantageous state and become dominant. We conjecture that this privilege is causing degenerated performance. Therefore, we propose to factor out this benefit with an auxiliary skip connection, ensuring a fairer competition for all operations. We call this approach DARTS-. Extensive experiments on various datasets verify that it can substantially improve robustness. Our code is available at https://github.com/Meituan-AutoML/DARTS- .

PaperPDFConference PDFCodeCode 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="2009.01027")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: official repository: 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Meituan-AutoML/DARTS- officialmentioned in paperpytorchApache-2.0 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

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 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.

8unverified

Licence: 0 of the 8 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 Meituan-AutoML/DARTS-. “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.

accuracy Meituan-AutoML/DARTS-/src/utils.py official repository unverified Apache-2.0 (permissive) · 469bf48752905889 · report
count_parameters_in_MB Meituan-AutoML/DARTS-/src/utils.py official repository unverified Apache-2.0 (permissive) · 3e816289579cc9e9 · report
gen_beta Meituan-AutoML/DARTS-/plots/plot_beta_vs_valid_loss.py official repository unverified Apache-2.0 (permissive) · a48bdfe2a6bf0357 · report
get_moving_average_3 Meituan-AutoML/DARTS-/plots/eigen_dist.py official repository unverified Apache-2.0 (permissive) · 30bb0400a2dd1188 · report
get_moving_average_5 Meituan-AutoML/DARTS-/plots/eigen_dist.py official repository unverified Apache-2.0 (permissive) · db90642e32525cb0 · report
read_json Meituan-AutoML/DARTS-/plots/plot_beta_vs_valid_loss.py official repository unverified Apache-2.0 (permissive) · 35394520b14b68c3 · report
singleton Meituan-AutoML/DARTS-/src/utils.py official repository unverified Apache-2.0 (permissive) · de6f3cc2917b53d0 · report
stop_criteria Meituan-AutoML/DARTS-/plots/eigen_dist.py official repository unverified Apache-2.0 (permissive) · 101678ccfacaef06 · report

Tasks

AutoMLNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search NAS-Bench-201, CIFAR-10 DARTS- Accuracy (Test) 93.80 #21 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DARTS- Accuracy (Val) 91.03 #21 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DARTS- Search time (s) 11520 #21 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DARTS- Accuracy (Test) 71.53 #22 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DARTS- Accuracy (Val) 71.36 #22 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 DARTS- Accuracy (Test) 45.12 #29 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 DARTS- Accuracy (Val) 44.87 #29 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