ReG-NAS: Graph Neural Network Architecture Search using Regression Proxy Task
Lists
Only you see this
Abstract
Neural Architecture Search (NAS) has become a focus that has been extensively researched in recent years. Innovative achievements are yielded from the area like convolutional neural networks (CNN), recurrent neural networks (RNN) and so on. However, research on NAS for graph neural networks (GNN) is still in a preliminary stage. Because of the special structure of graph data, some conclusions drew from CNN cannot be directly applied to GNN. At the same time, for NAS, the models' ranking stability is of great importance for it reflects the reliability of the NAS performance. Unfortunately, little research attention has been paid to it, making it a pitfall in the development of NAS research. In this paper, we proposed a novel NAS pipeline, ReG-NAS, which balances stability, reliability and time cost to search the best GNN architecture. Besides, for the first time, we systematically analyzed factors that will affect models' ranking stability in a given search space, which can be used as a guideline for subsequent studies. Our codes are available at https://anonymous.4open.science/r/ReG-NAS-4D21
BibTeX
@inproceedings{wei2023reg,
author = {Boyi Wei and Cong Hao},
title = {{ReG-NAS: Graph Neural Network Architecture Search using Regression Proxy Task}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=t7HIN3fUAUu},
}Loading related content...