NeurIPS 2020

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?


Meta Review

In the paper authors created an unsupervised learning method to embeds architectures in latent space and showed through experiments that the representations formed result in improved downstream performance compared to training with supervised objective jointly. The idea is important and the analysis is sound. The paper could be improved by analysing more diverse space of architectures than ResNet like blocks, as well as other suggestions given by the reviewers.