GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet

by   Shan You, et al.

Training a supernet matters for one-shot neural architecture search (NAS) methods since it serves as a basic performance estimator for different architectures (paths). Current methods mainly hold the assumption that a supernet should give a reasonable ranking over all paths. They thus treat all paths equally, and spare much effort to train paths. However, it is harsh for a single supernet to evaluate accurately on such a huge-scale search space (e.g., 7^21). In this paper, instead of covering all paths, we ease the burden of supernet by encouraging it to focus more on evaluation of those potentially-good ones, which are identified using a surrogate portion of validation data. Concretely, during training, we propose a multi-path sampling strategy with rejection, and greedily filter the weak paths. The training efficiency is thus boosted since the training space has been greedily shrunk from all paths to those potentially-good ones. Moreover, we further adopt an exploration and exploitation policy by introducing an empirical candidate path pool. Our proposed method GreedyNAS is easy-to-follow, and experimental results on ImageNet dataset indicate that it can achieve better Top-1 accuracy under same search space and FLOPs or latency level, but with only ∼60% of supernet training cost. By searching on a larger space, our GreedyNAS can also obtain new state-of-the-art architectures.


GreedyNASv2: Greedier Search with a Greedy Path Filter

Training a good supernet in one-shot NAS methods is difficult since the ...

MixPath: A Unified Approach for One-shot Neural Architecture Search

The expressiveness of search space is a key concern in neural architectu...

OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

Recently, neural architecture search (NAS) has been exploited to design ...

Guided Evolution for Neural Architecture Search

Neural Architecture Search (NAS) methods have been successfully applied ...

Single Path One-Shot Neural Architecture Search with Uniform Sampling

One-shot method is a powerful Neural Architecture Search (NAS) framework...

K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets

In one-shot weight sharing for NAS, the weights of each operation (at ea...

DetOFA: Efficient Training of Once-for-All Networks for Object Detection by Using Pre-trained Supernet and Path Filter

We address the challenge of training a large supernet for the object det...

Please sign up or login with your details

Forgot password? Click here to reset