Główne pojęcia
DiffusionNAG proposes a paradigm shift in Neural Architecture Generation by leveraging diffusion models to efficiently generate task-optimal architectures guided by property predictors.
Statystyki
DiffusionNAG achieves speedups of up to 35× on Transferable NAS benchmarks.
Cytaty
"DiffusionNAG significantly outperforms existing NAS methods in such experiments."