TY - JOUR
T1 - HGATE: Heterogeneous Graph Attention Auto-Encoders
AU - Wang, Wei
AU - Suo, Xiaoyang
AU - Wei, Xiangyu
AU - Wang, Bin
AU - Wang, Hao
AU - Dai, Hong Ning
AU - Zhang, Xiangliang
N1 - Generated from Scopus record by KAUST IRTS on 2023-09-20
PY - 2023/4/1
Y1 - 2023/4/1
N2 - Graph auto-encoder is considered a framework for unsupervised learning on graph-structured data by representing graphs in a low dimensional space. It has been proved very powerful for graph analytics. In the real world, complex relationships in various entities can be represented by heterogeneous graphs that contain more abundant semantic information than homogeneous graphs. In general, graph auto-encoders based on homogeneous graphs are not applicable to heterogeneous graphs. In addition, little work has been done to evaluate the effect of different semantics on node embedding in heterogeneous graphs for unsupervised graph representation learning. In this work, we propose a novel Heterogeneous Graph Attention Auto-Encoders (HGATE) for unsupervised representation learning on heterogeneous graph-structured data. Based on the consideration of semantic information, our architecture of HGATE reconstructs not only the edges of the heterogeneous graph but also node attributes, through stacked encoder/decoder layers. Hierarchical attention is used to learn the relevance between a node and its meta-path based neighbors, and the relevance among different meta-paths. HGATE is applicable to transductive learning as well as inductive learning. Node classification and link prediction experiments on real-world heterogeneous graph datasets demonstrate the effectiveness of HGATE for both transductive and inductive tasks.
AB - Graph auto-encoder is considered a framework for unsupervised learning on graph-structured data by representing graphs in a low dimensional space. It has been proved very powerful for graph analytics. In the real world, complex relationships in various entities can be represented by heterogeneous graphs that contain more abundant semantic information than homogeneous graphs. In general, graph auto-encoders based on homogeneous graphs are not applicable to heterogeneous graphs. In addition, little work has been done to evaluate the effect of different semantics on node embedding in heterogeneous graphs for unsupervised graph representation learning. In this work, we propose a novel Heterogeneous Graph Attention Auto-Encoders (HGATE) for unsupervised representation learning on heterogeneous graph-structured data. Based on the consideration of semantic information, our architecture of HGATE reconstructs not only the edges of the heterogeneous graph but also node attributes, through stacked encoder/decoder layers. Hierarchical attention is used to learn the relevance between a node and its meta-path based neighbors, and the relevance among different meta-paths. HGATE is applicable to transductive learning as well as inductive learning. Node classification and link prediction experiments on real-world heterogeneous graph datasets demonstrate the effectiveness of HGATE for both transductive and inductive tasks.
UR - https://ieeexplore.ieee.org/document/9664297/
UR - http://www.scopus.com/inward/record.url?scp=85122288661&partnerID=8YFLogxK
U2 - 10.1109/TKDE.2021.3138788
DO - 10.1109/TKDE.2021.3138788
M3 - Article
SN - 1558-2191
VL - 35
SP - 3938
EP - 3951
JO - IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
JF - IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
IS - 4
ER -