Are Labels Necessary For Neural Architecture Search? Probing Unsupervised Regimes Of AutoML

The performance of deep learning applications has improved proportionally with the increase in automation techniques such as Neural Architecture Search(NAS). Today hierarchical feature extractors are learned in an end-to-end fashion from data rather than manually designed.  NAS is the process of automating architecture engineering, a part of AutoML. NAS can be seen as a subfield of AutoML and has significant overlap with hyperparameter optimization and meta-learning. Researchers exploit the transferability of architectures to enable search to be performed on different data and labels. However, one thing common with the automated search and the traditional methods is that both need images and the (semantic) labels to search for an architecture. In other words, NAS flourish in the