PGRA: Projected graph relation-feature attention network for heterogeneous information network embedding
PGRA: Projected graph relation-feature attention network for heterogeneous information network embedding
复制标题
DOI：
10.1016/j.ins.2021.04.070
复制
发表时间：
2021-06-10
影响因子：
8.1
通讯作者：
Murata, Tsuyoshi
中科院分区：
文献类型：
--
作者：
Chairatanakul, Nuttapong;Liu, Xin;Murata, Tsuyoshi
图神经网络（GNN）已经取得了上级性能，并在各个领域获得了极大的兴趣。然而，大多数现有的GNN被认为是同构图，而现实世界的系统通常被建模为异构图或异构信息网络（HIN）。由于HIN中关系的异质性和不兼容性，设计GNN以完全捕获HIN的丰富语义信息是非常具有挑战性的。为了解决这些问题，同时利用GNN的力量，我们提出了一种新的无监督嵌入方法，称为投影图特征注意力网络（PGRA）。PGRA基于三种机制：1）将每个节点的表示向量投影到关系特定空间的特定关系投影，2）利用关系特征注意网络的聚合，该网络通过考虑节点的特征以及连接关系和目标关系之间的兼容性来学习聚合中的显著邻居，3）一个优雅设计的损失函数，它捕获了节点之间的一阶和二阶近似。在7个真实数据集上的大量实验结果表明，PGRA的性能大大优于最先进的方法。(c)2021年，任作家。爱思唯尔公司出版这是一个在CC BY许可证下的开放获取文章（http：//creativecommons.org/licenses/by/4.0/）。
Graph neural networks (GNNs) have achieved superior performance and gained significant interest in various domains. However, most of the existing GNNs are considered for homogeneous graphs, whereas real-world systems are usually modeled as heterogeneous graphs or heterogeneous information networks (HINs). Designing a GNN to fully capture the rich semantic information of HINs is significantly challenging owing to the heterogeneity and incompatibility of relations in HINs. To address these issues while utilizing the power of GNNs, we propose a novel unsupervised embedding approach, named Projected Graph Relation-Feature Attention Network (PGRA). PGRA is based on three mechanisms: 1) specific-relation projection that projects the representation vector of each node to a relation-specific space, 2) aggregation with a relation-feature attention network that learns salient neighbors in the aggregation by considering the features of the nodes and compatibility between the connected and target relations, 3) an elegantly designed loss function that captures both the first-and second-order proximities between nodes. The results of extensive experiments on seven real-world datasets illustrate that PGRA outperforms the state-of-the-art methods by a large margin.(c) 2021 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).