EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dual Lightweighting in Neural Architecture Search: Progressive Multi-Task Learning with Adaptive Model Complexity

Tao Wang, Yanqiang Di, Shaochong Feng, Haohao Cui, Qing Liu

Algorithms · 02.06.2026 · 19 (6) · 451

DOI: 10.3390/a19060451 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 02.06.2026. Verfasst von Tao Wang und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural architecture search (NAS) is a core technology in AutoML, but it faces challenges such as high computational costs and inefficient evaluation. Traditional NAS methods require fully training each candidate architecture, leading to substantial resource consumption and long evaluation times. This paper introduces a four-stage progressive multi-task learning framework that shifts from brute-force search to performance prediction. By progressively training from simple synthetic data to complex real data, the framework enables efficient architecture performance prediction. The main contributions are a unified progressive predictor paradigm, a deployment-aware multi-task prediction mechanism with dual lightweighting, and a benchmark-aware data-and-transfer framework based on NATS-Bench reconstruction and progressive knowledge distillation. Experiments on 15,000 NATS-Bench architectures with a fixed train–validation–test split (8:1:1) and consistent hyperparameters show a 95.56% correlation-based prediction score, computed as Pearson correlation expressed as a percentage (Pearson correlation 0.9556, R-squared 0.9134), 32-fold training efficiency improvement (37.87 s ± 2.1 s vs. 1247.6 s), and 95.7% convergence stability across five random seeds. Ablation studies, including a Direct Stage-3-Only comparison, quantify component contributions, and benchmarks compare against random forest, XGBoost, and MLP under identical data splits and feature spaces.

Zitieren

APA

Wang, T., Di, Y., Feng, S., Cui, H., & Liu, Q. (2026). Dual Lightweighting in Neural Architecture Search: Progressive Multi-Task Learning with Adaptive Model Complexity. Algorithms, 19(6), 451. https://doi.org/10.3390/a19060451

Vancouver

Wang T, Di Y, Feng S, Cui H, Liu Q. Dual Lightweighting in Neural Architecture Search: Progressive Multi-Task Learning with Adaptive Model Complexity. Algorithms. 2026;19(6):451. doi:10.3390/a19060451

BibTeX
@article{Wang2026,
  author = {Wang, Tao and Di, Yanqiang and Feng, Shaochong and Cui, Haohao and Liu, Qing},
  title = {Dual Lightweighting in Neural Architecture Search: Progressive Multi-Task Learning with Adaptive Model Complexity},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {6},
  pages = {451},
  doi = {10.3390/a19060451}
}
Kostenlos starten →