Timezone: »

 
Oral
Few-Shot Neural Architecture Search
Yiyang Zhao · Linnan Wang · Yuandong Tian · Rodrigo Fonseca · Tian Guo

Tue Jul 20 06:15 PM -- 06:35 PM (PDT) @ None

Efficient evaluation of a network architecture drawn from a large search space remains a key challenge in Neural Architecture Search (NAS). Vanilla NAS evaluates each architecture by training from scratch, which gives the true performance but is extremely time-consuming. Recently, one-shot NAS substantially reduces the computation cost by training only one supernetwork, a.k.a. supernet, to approximate the performance of every architecture in the search space via weight-sharing. However, the performance estimation can be very inaccurate due to the co-adaption among operations. In this paper, we propose few-shot NAS that uses multiple supernetworks, called sub-supernet, each covering different regions of the search space to alleviate the undesired co-adaption. Compared to one-shot NAS, few-shot NAS improves the accuracy of architecture evaluation with a small increase of evaluation cost. With only up to 7 sub-supernets, few-shot NAS establishes new SoTAs: on ImageNet, it finds models that reach 80.5% top-1 accuracy at 600 MB FLOPS and 77.5% top-1 accuracy at 238 MFLOPS; on CIFAR10, it reaches 98.72% top-1 accuracy without using extra data or transfer learning. In Auto-GAN, few-shot NAS outperforms the previously published results by up to 20%. Extensive experiments show that few-shot NAS significantly improves various one-shot methods, including 4 gradient-based and 6 search-based methods on 3 different tasks in NasBench-201 and NasBench1-shot-1.

Author Information

Yiyang Zhao (Worcester Polytechnic Institute)
Linnan Wang (Brown University)
Yuandong Tian (Facebook AI Research)
Rodrigo Fonseca (Brown University)
Tian Guo (Worcester Polytechnic Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors