Graph Embedding for Neural Architecture Search with Input-Output Information

Anonymous

Keywords: Neural Architecture Search, meta-features, graph variational autoencoder, semi-supervised learning

TL;DR: We extended an existing graph variational autoencoder for NAS to learn from input images and output features of a particular neural network in a semi-supervised manner.

Abstract: Graph representation learning has been used in neural architecture search, for example in performance prediction. Existing works focused mostly on neural graph similarity without considering functionally similar networks with different architectures. In this work, we adress this issue by using meta-information of input images and output features of a particular neural network. We extended the~arch2vec model, a graph variational autoencoder for neural architecture search, to learn from this novel kind of data. We demonstrate our approach on the NAS-Bench-101 search space and the CIFAR-10 dataset, and compare our model with the original arch2vec on a REINFORCE search task and a performance prediction task.