Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/105765
Title: | Auto-GNN : neural architecture search of graph neural networks | Authors: | Zhou, K Huang, X Song, Q Chen, R Hu, X |
Issue Date: | 2022 | Source: | Frontiers in big data, 2022, v. 5, 1029307 | Abstract: | Graph neural networks (GNNs) have been widely used in various graph analysis tasks. As the graph characteristics vary significantly in real-world systems, given a specific scenario, the architecture parameters need to be tuned carefully to identify a suitable GNN. Neural architecture search (NAS) has shown its potential in discovering the effective architectures for the learning tasks in image and language modeling. However, the existing NAS algorithms cannot be applied efficiently to GNN search problem because of two facts. First, the large-step exploration in the traditional controller fails to learn the sensitive performance variations with slight architecture modifications in GNNs. Second, the search space is composed of heterogeneous GNNs, which prevents the direct adoption of parameter sharing among them to accelerate the search progress. To tackle the challenges, we propose an automated graph neural networks (AGNN) framework, which aims to find the optimal GNN architecture efficiently. Specifically, a reinforced conservative controller is designed to explore the architecture space with small steps. To accelerate the validation, a novel constrained parameter sharing strategy is presented to regularize the weight transferring among GNNs. It avoids training from scratch and saves the computation time. Experimental results on the benchmark datasets demonstrate that the architecture identified by AGNN achieves the best performance and search efficiency, comparing with existing human-invented models and the traditional search methods. | Keywords: | Automated machine learning Deep and scalable graph analysis Graph neural networks Neural architecture search Reinforcement learning |
Publisher: | Frontiers Research Foundation | Journal: | Frontiers in big data | EISSN: | 2624-909X | DOI: | 10.3389/fdata.2022.1029307 | Rights: | © 2022 Zhou, Huang, Song, Chen and Hu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (http://creativecommons.org/licenses/by/4.0/). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. The following publication Zhou K, Huang X, Song Q, Chen R and Hu X (2022) Auto-GNN: Neural architecture search of graph neural networks. Front. Big Data 5:1029307 is available at https://doi.org/10.3389/fdata.2022.1029307. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
fdata-05-1029307.pdf | 1.17 MB | Adobe PDF | View/Open |
Page views
18
Citations as of Jun 30, 2024
Downloads
5
Citations as of Jun 30, 2024
SCOPUSTM
Citations
10
Citations as of Jul 4, 2024
WEB OF SCIENCETM
Citations
5
Citations as of Jul 4, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.