FTSO: Effective NAS via First Topology Second Operator

Understand

Existing one-shot neural architecture search (NAS) methods have to conduct a search over a giant super-net, which leads to the huge computational cost.

• To reduce such cost, in this paper, we propose a method, called FTSO, to divide the whole architecture search into two sub-steps.
• Specifically, in the first step, we only search for the topology, and in the second step, we search for the operators.
• FTSO not only reduces NAS's search time from days to 0.68 seconds, but also significantly improves the found architecture's accuracy.