Clustering Method based on VGAE Improving Interpretability of Search Results of Neural Architecture Search

DOI
  • HEMMI Kazuki
    University of Tsukuba National Institute of Advanced Industrial Science and Technology(AIST)
  • TANIGAKI Yuki
    National Institute of Advanced Industrial Science and Technology(AIST)
  • KAWAKAMI Kenta
    University of Tsukuba National Institute of Advanced Industrial Science and Technology(AIST)
  • ONISHI Masaki
    University of Tsukuba National Institute of Advanced Industrial Science and Technology(AIST)

Bibliographic Information

Other Title
  • VGAEを用いたNeural Architecture Searchの探索結果の解釈性向上を目指した構造クラスタリング手法

Abstract

<p>Neural Architecture Search (NAS) is a method of AutoML that the optimization of neural network models according to the given data and objectives. NAS needs a lot of time to search, and it is not efficient to search the network models from scratch for each new task. In other words, the improvement of NAS efficiency can be achieved by searching the architecture of similar models. The clustering and visualization of models based on their features are considered viable methods to search for similar network models. However, the quantitative classification of models based on their features is a challenge, and there is no widely known approach to visualize the features of models searched by NAS. Therefore, this study aims to obtain latent features of network models through a machine learning approach incorporating Variational Graph Auto-Encoders (VGAE), which is one of the graph neural network methods. As a result, the proposed method enables the search for similar network models and the comparisons between models.</p>

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top