Auto-GNN: Neural architecture search of graph neural networks

Simple item page
dc.citation.articleNumber1029307
dc.citation.journalTitleFrontiers in Big Data
dc.citation.volumeNumber5
dc.contributor.authorZhou, Kaixiong
dc.contributor.authorHuang, Xiao
dc.contributor.authorSong, Qingquan
dc.contributor.authorChen, Rui
dc.contributor.authorHu, Xia
dc.contributor.orgDATA Lab
dc.date.accessioned2023-01-27T14:47:27Z
dc.date.available2023-01-27T14:47:27Z
dc.date.issued2022
dc.description.abstractGraph 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.
dc.identifier.citationZhou, Kaixiong, Huang, Xiao, Song, Qingquan, et al.. "Auto-GNN: Neural architecture search of graph neural networks." <i>Frontiers in Big Data,</i> 5, (2022) Frontiers Media S.A.: https://doi.org/10.3389/fdata.2022.1029307.
dc.identifier.digitalfdata-05-1029307
dc.identifier.doihttps://doi.org/10.3389/fdata.2022.1029307
dc.identifier.urihttps://hdl.handle.net/1911/114276
dc.language.isoeng
dc.publisherFrontiers Media S.A.
dc.rightsThis is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). 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.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleAuto-GNN: Neural architecture search of graph neural networks
dc.typeJournal article
dc.type.dcmiText
dc.type.publicationpublisher version
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
fdata-05-1029307.pdf
Size:
1.14 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Computer Science Publications