Graph is all you need? Lightweight data-agnostic neural architecture search without training
This work addresses the computational bottleneck in NAS for researchers and practitioners, offering a lightweight alternative, though it is incremental as it builds on existing graph-based proxy methods.
The paper tackles the high computational cost of neural architecture search (NAS) by introducing a training-free, data-agnostic method that converts architectures to graphs and uses average degree as a proxy metric, reducing search time to 217 CPU seconds for 200 architectures and achieving competitive performance across multiple benchmarks.
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.