We thank all the reviewers for the valuable comments and suggestions

We thank all the reviewers for the valuable comments and suggestions. Besides, we indeed use dropout as in NoisyStudent (the paper you mentioned) to help generalization. We also combine SemiNAS with other NAS algorithm (e.g., Regularized Evolution) and We will add such experiments in the new version. SemiNAS (RE) consuming 2000 pairs to compare with RE under the same number of queries, and it achieves 94.03% CIFAR-10, there exist some differences. It runs each model for 3 times and collect the 3 results to reduce the variance.