Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks

Authors

  • Xin Chen Huawei Cloud & AI
  • Lingxi Xie Huawei Cloud & AI
  • Jun Wu Fudan University
  • Longhui Wei Huawei Cloud & AI
  • Yuhui Xu Shanghai Jiao Tong University
  • Qi Tian Huawei Cloud & AI

Keywords:

(Deep) Neural Network Algorithms

Abstract

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from which exponentially many sub-networks can be sampled and efficiently evaluated. These methods enjoy great advantages in terms of computational costs, but the sampled sub-networks are not guaranteed to be estimated precisely unless an individual training process is taken. This paper owes such inaccuracy to the inevitable mismatch between assembled network layers, so that there is a random error term added to each estimation. We alleviate this issue by training a graph convolutional network to fit the performance of sampled sub-networks so that the impact of random errors becomes minimal. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates, which consequently leads to better performance of the final architecture. In addition, our approach also enjoys the flexibility of being used under different hardware constraints, since the graph convolutional network has provided an efficient lookup table of the performance of architectures in the entire search space.

Downloads

Published

2021-05-18

How to Cite

Chen, X., Xie, L., Wu, J., Wei, L., Xu, Y., & Tian, Q. (2021). Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 7064-7072. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16869

Issue

Section

AAAI Technical Track on Machine Learning I