Citation: Hu, Q.; Lin, W.; Tang, M.;
Jiang, J. MBHAN: Motif-Based
Heterogeneous Graph Attention
Network. Appl. Sci. 2022, 12, 5931.
https://doi.org/10.3390/
app12125931
Academic Editors: Katia Lida
Kermanidis, Phivos Mylonas and
Manolis Maragoudakis
Received: 10 May 2022
Accepted: 9 June 2022
Published: 10 June 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
MBHAN: Motif-Based Heterogeneous Graph
Attention Network
Qian Hu
1,2,
*, Weiping Lin
2
, Minli Tang
2
and Jiatao Jiang
3
1
School of Media and Communications, Guizhou Normal University, Guiyang 550000, China
2
School of Informatics, Xiamen University, Xiamen 361000, China; linweiping@stu.xmu.edu.cn (W.L.);
tangml@stu.xmu.edu.cn (M.T.)
3
School of mathematical Science, Guizhou Normal University, Guiyang 550000, China; jjt@gznu.edu.cn
* Correspondence: huqian@gznu.edu.cn
Abstract:
Graph neural networks are graph-based deep learning technologies that have attracted
significant attention from researchers because of their powerful performance. Heterogeneous graph-
based graph neural networks focus on the heterogeneity of the nodes and links in a graph. This is
more effective at preserving semantic knowledge when representing data interactions in real-world
graph structures. Unfortunately, most heterogeneous graph neural networks tend to transform
heterogeneous graphs into homogeneous graphs when using meta-paths for representation learning.
This paper therefore presents a novel motif-based hierarchical heterogeneous graph attention network
algorithm, MBHAN, that addresses this problem by incorporating a hierarchical dual attention
mechanism at the node-level and motif-level. Node-level attention aims to learn the importance
between a node and its neighboring nodes within its corresponding motif. Motif-level attention is
capable of learning the importance of different motifs in the heterogeneous graph. In view of the
different vector space features of different types of nodes in heterogeneous graphs, MBHAN also
aggregates the features of different types of nodes, so that they can jointly participate in downstream
tasks after passing through segregated independent shallow neural networks. MBHAN’s superior
network representation learning capability has been validated by extensive experiments on two
real-world datasets.
Keywords:
heterogeneous graphs; graph neural networks; representation learning; motif; attention
mechanism
1. Introduction
Graph neural networks (GNNs) have attracted extensive attention in academia as a
powerful way of approaching deep representation learning for graph data. They have
been proven to perform especially well in network analysis [
1
,
2
]. The basic idea of a graph
neural network is to undertake representation learning on the nodes themselves, according
to their local neighborhood information. This involves aggregating the information of
each node and its surrounding nodes through a neural network. So, in [
3
–
5
], the node
features and graph structure in graphs are used to learn node embeddings. Convolutional
operations can also be introduced into graph representation learning [6–9].
Alongside GNNs, a significant amount of interest has been shown to attention mecha-
nisms [
10
], which encourage models to focus on the most salient parts of the data that will
affect downstream tasks. Attention mechanisms have been highly effective when incorpo-
rated into deep neural network frameworks and are widely used across a range of different
domains [
11
–
15
]. Graph Attention Networks (GAT) [
16
] assume that different neighboring
nodes may play different roles for the core nodes. A self-attention mechanism can therefore
be employed [
17
] to aggregate neighbor nodes and achieve an adaptive matching of weights
that captures the different importance of different neighbors. However, GAT can only be
applied to homogeneous graphs and cannot be easily migrated to heterogeneous graphs.
Appl. Sci. 2022, 12, 5931. https://doi.org/10.3390/app12125931 https://www.mdpi.com/journal/applsci
