Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks

计算机科学 统计关系学习 理论计算机科学 节点(物理) 图形 班级(哲学) 编码器 关系演算 对偶(语法数字) 关系数据库 关系模型 人工智能 数据挖掘 工程类 文学类 艺术 操作系统 结构工程
作者
Zhiwen Yu,Wei Sang,Huaming Du,Xingyan Chen,Li,Fuzhen Zhuang,Ji Liu,Gang Kou
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2112.13078
摘要

Bi-type multi-relational heterogeneous graph (BMHG) is one of the most common graphs in practice, for example, academic networks, e-commerce user behavior graph and enterprise knowledge graph. It is a critical and challenge problem on how to learn the numerical representation for each node to characterize subtle structures. However, most previous studies treat all node relations in BMHG as the same class of relation without distinguishing the different characteristics between the intra-class relations and inter-class relations of the bi-typed nodes, causing the loss of significant structure information. To address this issue, we propose a novel Dual Hierarchical Attention Networks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-class and inter-class attention-based encoder under a hierarchical mechanism. Specifically, the former encoder aggregates information from the same type of nodes, while the latter aggregates node representations from its different types of neighbors. Moreover, to sufficiently model node multi-relational information in BMHG, we adopt a newly proposed hierarchical mechanism. By doing so, the proposed dual hierarchical attention operations enable our model to fully capture the complex structures of the bi-typed multi-relational heterogeneous graphs. Experimental results on various tasks against the state-of-the-arts sufficiently confirm the capability of DHAN in learning node representations on the BMHGs.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
脑洞疼应助小白采纳,获得10
1秒前
秋雪瑶应助hx60606采纳,获得10
3秒前
sunyafei完成签到 ,获得积分10
3秒前
orixero应助FORWORD采纳,获得10
3秒前
5秒前
6秒前
Jack80发布了新的文献求助30
8秒前
打打应助Ta沓如流星采纳,获得10
9秒前
10秒前
爆米花应助默然的歌采纳,获得10
10秒前
gjww应助WU采纳,获得10
11秒前
图图完成签到 ,获得积分10
11秒前
富婆嘉嘉子应助熊啾啾采纳,获得20
11秒前
邢邢完成签到,获得积分10
12秒前
赘婿应助wolf采纳,获得10
12秒前
小白完成签到,获得积分10
12秒前
13秒前
centlay应助hx60606采纳,获得10
13秒前
14秒前
xxxxx应助.....采纳,获得10
14秒前
FORWORD发布了新的文献求助10
15秒前
15秒前
李健应助小小少年采纳,获得10
16秒前
17秒前
NHN完成签到,获得积分20
18秒前
18秒前
小白发布了新的文献求助10
18秒前
18秒前
共享精神应助paper reader采纳,获得10
19秒前
猫猫咪呀发布了新的文献求助10
19秒前
Teanka完成签到,获得积分10
19秒前
21秒前
默然的歌发布了新的文献求助10
22秒前
苹果白凡发布了新的文献求助10
22秒前
wlnhyF发布了新的文献求助10
24秒前
迦佭完成签到,获得积分10
25秒前
25秒前
肥羊七号完成签到 ,获得积分10
26秒前
费胜发布了新的文献求助10
26秒前
RMgX完成签到,获得积分10
27秒前
高分求助中
Heun’s Differential Equations 600
《Fundamentals of Power Supply Design》Robert A. Mammano 510
Characteristics and Origin of the Mantle Root Beneath the Murowa Diamond Mine: Implications for Craton and Diamond Formation* 300
High Wire: How China Regulates Big Tech and Governs Its Economy 260
lingnan science journal vol. 16 250
The philosophy of sports medicine care: an historical review 250
A posteriori勾配制限手法「ポストリミタ」と界面捕獲法THINCを組み合わせた連続・不連続流れを高解像するMUSCLタイプの解法 210
热门求助领域 (近24小时)
化学 材料科学 医学 生物 有机化学 工程类 生物化学 纳米技术 物理 内科学 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 电极 光电子学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 2250936
求助须知:如何正确求助?哪些是违规求助? 1899783
关于积分的说明 4741260
捐赠科研通 1689677
什么是DOI,文献DOI怎么找? 856691
版权声明 545483
科研通“疑难数据库(出版商)”最低求助积分说明 453632