Can I read Homogeneous Architecture Augmentation for Neural Predictor on EtoBox?

Homogeneous Architecture Augmentation for Neural Predictor by Liu, Yuqiao; Tang, Yehui; Sun, Yanan is a scholarly article available to read on EtoBox.

What is Homogeneous Architecture Augmentation for Neural Predictor about?

Neural Architecture Search (NAS) can automatically design well-performed architectures of Deep Neural Networks (DNNs) for the tasks at hand. However, one bottleneck of NAS is the prohibitively computational cost largely due to the expensive performance evaluation. The neural predictors can directly estimate the performance without any training of the DNNs to be evaluated, thus have drawn increasing attention from researchers. Despite their popularity, they also suffer a severe limitation: the shortage of annotated DNN architectures for effectively training the neural predictors. In this paper, we proposed Homogeneous Architecture Augmentation for Neural Predictor (HAAP) of DNN architectures to address the issue aforementioned. Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation. Furthermore, the one-hot encoding strategy is introduced into HAAP to make the representation of DNN architectures more effective. The experiments have been conducted on both NAS-Benchmark-101 and NAS-Bench-201 dataset. The experimental results demonstrate that the proposed HAAP algorithm outper

Author

Liu, Yuqiao; Tang, Yehui; Sun, Yanan

Published

2021

Language

EN