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.
Yang YAN
Tianjin University of Technology and Education
Qiuyan WANG
Tiangong University
Lin LIU
Tianjin LINHAITEC Ltd.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yang YAN, Qiuyan WANG, Lin LIU, "Latent Influence Based Self-Attention Framework for Heterogeneous Network Embedding" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 7, pp. 1335-1339, July 2022, doi: 10.1587/transinf.2021EDL8093.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8093/_p
Copy
@ARTICLE{e105-d_7_1335,
author={Yang YAN, Qiuyan WANG, Lin LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Latent Influence Based Self-Attention Framework for Heterogeneous Network Embedding},
year={2022},
volume={E105-D},
number={7},
pages={1335-1339},
abstract={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.},
keywords={},
doi={10.1587/transinf.2021EDL8093},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Latent Influence Based Self-Attention Framework for Heterogeneous Network Embedding
T2 - IEICE TRANSACTIONS on Information
SP - 1335
EP - 1339
AU - Yang YAN
AU - Qiuyan WANG
AU - Lin LIU
PY - 2022
DO - 10.1587/transinf.2021EDL8093
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2022
AB - 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.
ER -