Papers › PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search
PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search
Yameng Peng, Andy Song, Vic Ciesielski, Haytham M. Fayek, Xiaojun Chang
Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space during the search. Prediction of the networks' performance can alleviate this high computational overhead by mitigating the need for evaluating every candidate network. Developing such a predictor typically requires a large number of evaluated architectures which may be difficult to obtain. We address this challenge by proposing a novel evolutionary-based NAS strategy, Predictor-assisted E-NAS (PRE-NAS), which can perform well even with an extremely small number of evaluated architectures. PRE-NAS leverages new evolutionary search strategies and integrates high-fidelity weight inheritance over generations. Unlike one-shot strategies, which may suffer from bias in the evaluation due to weight sharing, offspring candidates in PRE-NAS are topologically homogeneous, which circumvents bias and leads to more accurate predictions. Extensive experiments on NAS-Bench-201 and DARTS search spaces show that PRE-NAS can outperform state-of-the-art NAS methods. With only a single GPU searching for 0.6 days, competitive architecture can be found by PRE-NAS which achieves 2.40% and 24% test error rates on CIFAR-10 and ImageNet respectively.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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
1 archive task tag without a task page not shown.
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 | PRE-NAS | Accuracy (Test) | 94.04 | #17 of 37 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, CIFAR-10 | PRE-NAS | Accuracy (Val) | 91.37 | #17 of 37 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, CIFAR-100 | PRE-NAS | Accuracy (Test) | 72.02 | #18 of 40 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, CIFAR-100 | PRE-NAS | Accuracy (Val) | 71.95 | #18 of 40 | Archive leaderboard | report |
| Neural Architecture Search | NAS-Bench-201, ImageNet-16-120 | PRE-NAS | Accuracy (Test) | 45.34 | #28 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