Auto-GNN: Neural architecture search of graph neural networks

Kaixiong Zhou, Xiao Huang, Qingquan Song, Rui Chen, Xia Hu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

12 Citations (Scopus)


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.

Original languageEnglish
Article number1029307
Pages (from-to)1-12
JournalFrontiers in Big Data
Publication statusPublished - 17 Nov 2022


  • automated machine learning
  • deep and scalable graph analysis
  • graph neural networks
  • neural architecture search
  • reinforcement learning

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Information Systems
  • Artificial Intelligence


Dive into the research topics of 'Auto-GNN: Neural architecture search of graph neural networks'. Together they form a unique fingerprint.

Cite this