Binarized graph neural network

Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, Xiangjian He, Yiguang Lin, Xuemin Lin

Research output: Journal PublicationArticlepeer-review

13 Citations (Scopus)

Abstract

Recently, there have been some breakthroughs in graph analysis by applying the graph neural networks (GNNs) following a neighborhood aggregation scheme, which demonstrate outstanding performance in many tasks. However, we observe that the parameters of the network and the embedding of nodes are represented in real-valued matrices in existing GNN-based graph embedding approaches which may limit the efficiency and scalability of these models. It is well-known that binary vector is usually much more space and time efficient than the real-valued vector. This motivates us to develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters following the GNN-based paradigm. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding. Extensive experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space while matching the state-of-the-art performance.

Original languageEnglish
Pages (from-to)825-848
Number of pages24
JournalWorld Wide Web
Volume24
Issue number3
DOIs
Publication statusPublished - May 2021
Externally publishedYes

Keywords

  • Binarized neural network
  • Classification
  • Graph neural network

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Binarized graph neural network'. Together they form a unique fingerprint.

Cite this