Graph is all you need? Lightweight data-agnostic neural architecture search without training

arXiv:2405.01306v1 Announce Type: new
Abstract: 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 …

abstract algorithm architecture architectures arxiv computational costs cs.lg data design evaluation generated graph graphs however nas network neural architectures neural architecture search neural network performance search training type