Papers › PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search

PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search

12 Jul 2019ICLR 2020 1arXiv:1907.05737archive 2025-07-28

Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, Hongkai Xiong

Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture. In this paper, we present a novel approach, namely, Partially-Connected DARTS, by sampling a small part of super-network to reduce the redundancy in exploring the network space, thereby performing a more efficient search without comprising the performance. In particular, we perform operation search in a subset of channels while bypassing the held out part in a shortcut. This strategy may suffer from an undesired inconsistency on selecting the edges of super-net caused by sampling different channels. We alleviate it using edge normalization, which adds a new set of edge-level parameters to reduce uncertainty in search. Thanks to the reduced memory cost, PC-DARTS can be trained with a larger batch size and, consequently, enjoys both faster speed and higher training stability. Experimental results demonstrate the effectiveness of the proposed method. Specifically, we achieve an error rate of 2.57% on CIFAR10 with merely 0.1 GPU-days for architecture search, and a state-of-the-art top-1 error rate of 24.2% on ImageNet (under the mobile setting) using 3.8 GPU-days for search. Our code has been made available at: https://github.com/yuhuixu1993/PC-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="1907.05737")

Code

Syntology Ran 1 of 11 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 11 samples from 2 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yuhuixu1993/PC-DARTS officialmentioned in papermentioned on GitHubpytorch report
aragakiyuiii/gumbel-pdarts-master mentioned on GitHubpytorchNOASSERTION report
chenxin061/pdarts mentioned on GitHubpytorch report
ddghost/new_darts mentioned on GitHubpytorch report
peteryuX/pcdarts-tf2 mentioned on GitHubtfMIT report
xkp793003821/PC-DARTS-COOPER mentioned on GitHubpytorch 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

11 samples harvested; 1 ran; 0 honoured the contract we drafted; 10 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
10unverified

Licence: 1 of the 11 samples is 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

channel_shuffle ddghost/new_darts/model_search.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · b9da06d4f527dd6c · report
CosineAnnealingLR peteryuX/pcdarts-tf2/modules/lr_scheduler.py community (archive-listed) unverified MIT (permissive) · 40295363538b7b37 · report
CosineAnnealingLR_Restart peteryuX/pcdarts-tf2/modules/lr_scheduler.py community (archive-listed) unverified MIT (permissive) · 9dc6f449a229fadb · report
MultiStepLR peteryuX/pcdarts-tf2/modules/lr_scheduler.py community (archive-listed) unverified MIT (permissive) · 9e0df5e5f87592dc · report
accuracy peteryuX/pcdarts-tf2/modules/utils.py community (archive-listed) unverified MIT (permissive) · a254b5f92907af68 · report
channel_shuffle peteryuX/pcdarts-tf2/modules/models_search.py community (archive-listed) unverified MIT (permissive) · db7afeb6a845da40 · report
count_parameters_in_MB peteryuX/pcdarts-tf2/modules/utils.py community (archive-listed) unverified MIT (permissive) · c936ca3fba6360d8 · report
drop_path peteryuX/pcdarts-tf2/modules/operations.py community (archive-listed) unverified MIT (permissive) · 62658d26ba90a118 · report
kernel_init peteryuX/pcdarts-tf2/modules/operations.py community (archive-listed) unverified MIT (permissive) · f7ac8f51ad1ff8d2 · report
load_yaml peteryuX/pcdarts-tf2/modules/utils.py community (archive-listed) unverified MIT (permissive) · c6d8e748cf074438 · report
regularizer peteryuX/pcdarts-tf2/modules/operations.py community (archive-listed) unverified MIT (permissive) · d77031ce61c7c059 · report

Tasks

Neural Architecture Search

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 PC-DARTS-CIFAR Top-1 Error Rate 2.51% #20 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 PC-DARTS Parameters 3.6M #27 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 PC-DARTS Search Time (GPU days) 0.1 #27 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 PC-DARTS Top-1 Error Rate 2.57% #27 of 41 Archive leaderboard report
Neural Architecture Search ImageNet PC-DARTS (ImageNet) Accuracy 75.8 #102 of 135 Archive leaderboard report
Neural Architecture Search ImageNet PC-DARTS (ImageNet) MACs 597M #102 of 135 Archive leaderboard report
Neural Architecture Search ImageNet PC-DARTS (ImageNet) Params 5.3M #102 of 135 Archive leaderboard report
Neural Architecture Search ImageNet PC-DARTS (ImageNet) Top-1 Error Rate 24.2 #102 of 135 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

DARTSSPEED

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