Attentive Graph-based Recursive Neural Network for collective vertex classification

Qiongkai Xu, Qing Wang, Chenchen Xu, Lizhen Qu

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)


Vertex classification is a critical task in graph analysis, where both contents and linkage of vertices are incorporated during classification. Recently, researchers proposed using deep neural network to build an end-to-end framework, which can capture both local content and structure information. These approaches were proved effective in incorporating semantic meanings of neighbouring vertices, while the usefulness of this information was not properly considered. In this paper, we propose an Attentive Graph-based Recursive Neural Network (AGRNN), which exerts attention on neural network to make our model focus on vertices with more relevant semantic information. We evaluated our approach on three real-world datasets and also datasets with synthetic noise. Our experimental results show that AGRNN achieves the state-of-the-art performance, in terms of effectiveness and robustness. We have also illustrated some attention weight samples to demonstrate the rationality of our model.

Original languageEnglish
Title of host publicationProceedings of the 2017 ACM Conference on Information and Knowledge Management
EditorsShane Culpepper, Eric Lo, Joyce Ho
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages4
ISBN (Electronic)9781450349185
Publication statusPublished - 2017
Externally publishedYes
EventACM International Conference on Information and Knowledge Management 2017 - Singapore, Singapore
Duration: 6 Nov 201710 Nov 2017
Conference number: 26th


ConferenceACM International Conference on Information and Knowledge Management 2017
Abbreviated titleCIKM 2017
Internet address


  • Attention model
  • Collective vertex classification
  • Recursive neural network

Cite this