Papers › Differentiable Architecture Search with Random Features
Differentiable Architecture Search with Random Features
Xuanyang Zhang, Yonggang Li, Xiangyu Zhang, Yongtao Wang, Jian Sun
Differentiable architecture search (DARTS) has significantly promoted the development of NAS techniques because of its high search efficiency and effectiveness but suffers from performance collapse. In this paper, we make efforts to alleviate the performance collapse problem for DARTS from two aspects. First, we investigate the expressive power of the supernet in DARTS and then derive a new setup of DARTS paradigm with only training BatchNorm. Second, we theoretically find that random features dilute the auxiliary connection role of skip-connection in supernet optimization and enable search algorithm focus on fairer operation selection, thereby solving the performance collapse problem. We instantiate DARTS and PC-DARTS with random features to build an improved version for each named RF-DARTS and RF-PCDARTS respectively. Experimental results show that RF-DARTS obtains \textbf{94.36\%} test accuracy on CIFAR-10 (which is the nearest optimal result in NAS-Bench-201), and achieves the newest state-of-the-art top-1 test error of \textbf{24.0\%} on ImageNet when transferring from CIFAR-10. Moreover, RF-DARTS performs robustly across three datasets (CIFAR-10, CIFAR-100, and SVHN) and four search spaces (S1-S4). Besides, RF-PCDARTS achieves even better results on ImageNet, that is, \textbf{23.9\%} top-1 and \textbf{7.1\%} top-5 test error, surpassing representative methods like single-path, training-free, and partial-channel paradigms directly searched on ImageNet.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Neural Architecture Search | NAS-Bench-201, CIFAR-10 | RF-DARTS | Accuracy (Test) | 94.27 | #13 of 37 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, CIFAR-10 | RF-DARTS | Accuracy (Val) | 91.3 | #13 of 37 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, CIFAR-100 | RF-DARTS | Accuracy (Test) | 72.94 | #14 of 40 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, CIFAR-100 | RF-DARTS | Accuracy (Val) | 72.95 | #14 of 40 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, ImageNet-16-120 | RF-DARTS | Accuracy (Test) | 46.1 | #20 of 49 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, ImageNet-16-120 | RF-DARTS | Accuracy (Val) | 46.40 | #20 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
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