Papers › DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search

DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search

23 Nov 2021BMVC 2021 11archive 2025-07-28

Shun Lu, Yu Hu, Longxing Yang, Zihao Sun, Jilin Mei, Yiming Zeng, Xiaowei Li

Differentiable Neural Architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency. However, the competition of candidate operations in DARTS introduces high uncertainty for selecting the truly important operation, thus leading to serious performance collapse. In this work, we decrease the uncertainty of differentiable architecture search (DU-DARTS) by enforcing the distribution of architecture parameters to approach the one-hot categorical distribution and by replacing the zero operation with a gate switch. Without any extra search cost, our method achieves state-of-the-art performance with 2.32%, 16.74%, and 24.1% test error on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively. Moreover, DU-DARTS can robustly find an excellent architecture on NAS-Bench-1Shot1 and NAS-Bench-201, which further demonstrates the effectiveness of our method. The source code is available at https://github.com/ShunLu91/DU-DARTS.

PaperPDFCode

Code

ShunLu91/DU-DARTS mentioned in paperpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Neural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 DU-DARTS Parameters 3.8M #11 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 DU-DARTS Search Time (GPU days) 0.4 #11 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 DU-DARTS Top-1 Error Rate 2.32% #11 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-100 DU-DARTS PARAMS 3.1M #9 of 13 Archive leaderboard report
Neural Architecture Search CIFAR-100 DU-DARTS Percentage Error 16.74 #9 of 13 Archive leaderboard report
Neural Architecture Search ImageNet DU-DARTS Accuracy 75.9 #100 of 135 Archive leaderboard report
Neural Architecture Search ImageNet DU-DARTS Params 5.3M #100 of 135 Archive leaderboard report
Neural Architecture Search ImageNet DU-DARTS Top-1 Error Rate 24.1 #100 of 135 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DU-DARTS Accuracy (Test) 93.86 #20 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 DU-DARTS Accuracy (Val) 91.21 #20 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DU-DARTS Accuracy (Test) 71.84 #20 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 DU-DARTS Accuracy (Val) 71.88 #20 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 DU-DARTS Accuracy (Test) 45.94 #22 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.

Methods

DARTS

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