Neural architecture search (NAS) enables the automatic design of neural network models. However, training the candidates generated by the search algorithm for performance evaluation incurs considerable computational overhead. Our method, dubbed nasgraph, remarkably reduces the computational costs by converting neural architectures to graphs and using the average degree, a graph measure, as the proxy in lieu of the evaluation metric. Our training-free NAS method is data-agnostic and light-weight. It can find the best architecture among 200 randomly sampled architectures from NAS-Bench201 in 217 CPU seconds. Besides, our method is able to achieve competitive performance on various datasets including NASBench-101, NASBench-201, and NDS search spaces. We also demonstrate that nasgraph generalizes to more challenging tasks on Micro TransNAS-Bench-101.

翻译：神经架构搜索（NAS）能够自动设计神经网络模型。然而，对搜索算法生成的候选架构进行训练以评估其性能会带来大量的计算开销。我们的方法名为nasgraph，通过将神经架构转换为图，并采用图的平均度数这一图度量指标作为评估指标的替代代理，显著降低了计算成本。这种免训练的NAS方法无需依赖特定数据且轻量高效。它能在217秒的CPU时间内，从NAS-Bench201中随机采样的200个架构中找出最优架构。此外，我们的方法在多个数据集（包括NASBench-101、NASBench-201和NDS搜索空间）上均能取得具有竞争力的性能。我们还证明了nasgraph能够泛化应用于Micro TransNAS-Bench-101上更具挑战性的任务。