API-GNN: Attribute preserving oriented interactive graph neural network

Yuchen ZHOU, Yanmin SHANG, Yanan CAO, Qian LI, Chuan ZHOU, Guandong XU

Research output: Contribution to journalArticlespeer-review

4 Citations (Scopus)


Attributed graph embedding aims to learn node representation based on the graph topology and node attributes. The current mainstream GNN-based methods learn the representation of the target node by aggregating the attributes of its neighbor nodes. These methods still face two challenges: (1) In the neighborhood aggregation procedure, the attributes of each node would be propagated to its neighborhoods which may cause disturbance to the original attributes of the target node and cause over-smoothing in GNN iteration. (2) Because the representation of the target node is derived from the attributes and topology of its neighbors, the attributes and topological information of each neighbor have different effects on the representation of the target node. However, this different contribution has not been considered by the existing GNN-based methods. In this paper, we propose a novel GNN model named API-GNN (Attribute Preserving Oriented Interactive Graph Neural Network). API-GNN can not only reduce the disturbance of neighborhood aggregation to the original attribute of target node, but also explicitly model the different impacts of attribute and topology on node representation. We conduct experiments on six public real-world datasets to validate API-GNN on node classification and link prediction. Experimental results show that our model outperforms several strong baselines over various graph datasets on multiple graph analysis tasks. Copyright © 2022 Springer. 

Original languageEnglish
Pages (from-to)239-258
JournalWorld Wide Web
Early online dateJan 2022
Publication statusPublished - 2022


Zhou, Y., Shang, Y., Cao, Y., Li, Q., Zhou, C., & Xu, G. (2022). API-GNN: Attribute preserving oriented interactive graph neural network. World Wide Web, 25, 239-258. https://doi.org/10.1007/s11280-021-00987-z


  • Data mining
  • Graph neural networks
  • Social analysis
  • Representation learning


Dive into the research topics of 'API-GNN: Attribute preserving oriented interactive graph neural network'. Together they form a unique fingerprint.