The search functionality is under construction.
The search functionality is under construction.

Latent Influence Based Self-Attention Framework for Heterogeneous Network Embedding

Yang YAN, Qiuyan WANG, Lin LIU

  • Full Text Views

    0

  • Cite this

Summary :

In recent years, Graph Neural Networks has received enormous attention from academia for its huge potential of modeling the network traits such as macrostructure and single node attributes. However, prior mainstream works mainly focus on homogeneous network and lack the capacity to characterize the network heterogeneous property. Besides, most previous literature cannot the model latent influence link under microscope vision, making it infeasible to model the joint relation between the heterogeneity and mutual interaction within multiple relation type. In this letter, we propose a latent influence based self-attention framework to address the difficulties mentioned above. To model the heterogeneity and mutual interactions, we redesign the attention mechanism with latent influence factor on single-type relation level, which learns the importance coefficient from its adjacent neighbors under the same meta-path based patterns. To incorporate the heterogeneous meta-path in a unified dimension, we developed a novel self-attention based framework for meta-path relation fusion according to the learned meta-path coefficient. Our experimental results demonstrate that our framework not only achieves higher results than current state-of-the-art baselines, but also shows promising vision on depicting heterogeneous interactive relations under complicated network structure.

Publication
IEICE TRANSACTIONS on Information Vol.E105-D No.7 pp.1335-1339
Publication Date
2022/07/01
Publicized
2022/03/24
Online ISSN
1745-1361
DOI
10.1587/transinf.2021EDL8093
Type of Manuscript
LETTER
Category
Artificial Intelligence, Data Mining

Authors

Yang YAN
  Tianjin University of Technology and Education
Qiuyan WANG
  Tiangong University
Lin LIU
  Tianjin LINHAITEC Ltd.

Keyword