Neural architecture search using network embedding and generative adversarial networks

Surrogate models are used by recently proposed algorithms as a means of forecasting neural architecture performance. Rather than training the network from scratch, which speeds up evaluation of performance in the search for neural architecture. However, collecting a sufficient number of labeled architectures for training surrogate models is a time-consuming process. We suggest a surrogate-assisted swarm optimization algorithm with network embedding for neural architecture search, as well as a generative adversarial networks for augmentation data (GNE-NAS) to improve the performance of surrogate models with limited training data. In this case, each architecture is meaningfully represented using an unsupervised learning technique. In the embedding space, architectures with a greater degree of structural similarity are positioned closer together. This proximity facilitates the training of surrogate models. Prior to training the surrogate model, we employ a generative adversarial network for data augmentation. This approach enhances the robustness of the surrogate model and concurrently reduces the need for a large number of real evaluations. The surrogate model achieves comparable or better performance when network embedding is applied, as demonstrated by experimental results on two distinct NASBench search spaces. Our proposed method, GNE-NAS, has been shown to outperform other state-of-the-art neural architecture search algorithms.