Context-sensitive graph representation learning

Jisheng Qin, Xiaoqin Zeng, Shengli Wu, Yang Zou

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
59 Downloads (Pure)


Graph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic Aligned Graph Convolutional Network (MSAGCN), which contains two fundamental operations: multi-angle aggregation and semantic alignment, to resolve two challenges simultaneously. The core of MSAGCN is the aggregation of nodes that belong to the same class from three perspectives: nodes, features, and graph structure, and expects the obtained node features to be mapped nearby. Specifically, multi-angle aggregation is applied to extract features from three angles of the labelled nodes, and semantic alignment is utilised to align the semantics in the extracted features to enhance the similar content from different angles. In this way, the problem of over-smoothing and over-fitting for GCN can be alleviated. We perform the node clustering task on three citation datasets, and the experimental results demonstrate that our method outperforms the state-of-the-art (SOTA) baselines.
Original languageEnglish
Pages (from-to)2313-2331
Number of pages19
JournalConnection Science
Issue number1
Early online date14 Sept 2022
Publication statusPublished (in print/issue) - 31 Dec 2022

Bibliographical note

Funding Information:
This work was supported by the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX21_0484).

Publisher Copyright:
© 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.


  • Artificial Intelligence
  • Human-Computer Interaction
  • Software
  • Graph convolutional network
  • GCN
  • semantic alignment
  • multi-semantic alignment


Dive into the research topics of 'Context-sensitive graph representation learning'. Together they form a unique fingerprint.

Cite this