HyGGE: Hyperbolic graph attention network for reasoning over knowledge graphs

嵌入 双曲空间 理论计算机科学 计算机科学 双曲流形 关系(数据库) 数学 图形 欧几里德几何 纯数学 人工智能 双曲函数 数据挖掘 几何学
作者
Yuzhuo Wang,Hongzhi Wang,Wenbo Lu,Yanguang Yu
出处
期刊:Information Sciences [Elsevier BV]
卷期号:630: 190-205 被引量:15
标识
DOI:10.1016/j.ins.2023.02.050
摘要

Recently, hyperbolic embedding has successfully demonstrated its superiority over Euclidean analogues in representing hierarchical data. As the scale-free network that usually exhibits rich hierarchical structures, knowledge graphs naturally become a field where hyperbolic embedding shows its talents. Furthermore, hyperbolic embedding is also an expected solution to comprehensively reproduce the semantic features and underlying structures of KGs in the embedding space, which will significantly optimize the interpretability and performance of embedding models. However, most of the several existing hyperbolic studies only individually learn semantic information indicated by triples individually, making the embedding space relatively one-sided and simplified. In addition, many issues that limit reasoning performance are still ignored and unresolved in the context of hyperbolic geometry, like the response to complex relations and relation patterns. Motivated by these concerns, we propose the hyperbolic embedding model for KG reasoning, HyGGE. It is based on an innovative hyperbolic graph attention network. Furthermore, the response to complex relations, which is a well-known problem that constrains reasoning performance is also discussed in HyGGE. On the one hand, the focus on neighborhood structures and relation features makes up for the singularity that the embedding space is completely induced by triples individually, thereby optimizing the expressiveness of the embedding space. On the other hand, they cooperate with the effect of hyperbolic geometry to capture hierarchical features contained in local structures, and thus giving the hyperbolic embedding a fuller play to its advantages. Extensive experiments have validated the effectiveness and advantages of HyGGE.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Lulu发布了新的文献求助10
1秒前
所所应助笨脑腐采纳,获得10
2秒前
天天快乐应助笨脑腐采纳,获得10
2秒前
小小富应助笨脑腐采纳,获得10
2秒前
小小富应助笨脑腐采纳,获得10
2秒前
英姑应助笨脑腐采纳,获得10
2秒前
情怀应助yiran采纳,获得10
4秒前
myheng完成签到 ,获得积分10
5秒前
6秒前
田様应助笨脑腐采纳,获得10
8秒前
万能图书馆应助笨脑腐采纳,获得10
8秒前
SciGPT应助笨脑腐采纳,获得10
8秒前
打打应助笨脑腐采纳,获得10
8秒前
丘比特应助笨脑腐采纳,获得10
8秒前
充电宝应助笨脑腐采纳,获得10
8秒前
慕青应助笨脑腐采纳,获得10
8秒前
思源应助笨脑腐采纳,获得10
8秒前
情怀应助笨脑腐采纳,获得10
8秒前
Orange应助笨脑腐采纳,获得10
8秒前
9秒前
Rondab应助赵小漂亮采纳,获得10
9秒前
无糖零脂发布了新的文献求助10
9秒前
李爱国应助Wine1022采纳,获得10
9秒前
末日的阳光完成签到 ,获得积分10
10秒前
深情安青应助Juanita采纳,获得10
10秒前
11秒前
何照人应助郑宇航采纳,获得10
11秒前
12秒前
loong发布了新的文献求助10
13秒前
13秒前
miaomiao完成签到,获得积分10
14秒前
燕燕于飞发布了新的文献求助10
16秒前
17秒前
17秒前
要减肥含灵完成签到,获得积分10
17秒前
17秒前
chandlusf完成签到,获得积分10
19秒前
研友_VZG7GZ应助勤奋大地采纳,获得10
19秒前
19秒前
20秒前
高分求助中
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 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 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3963764
求助须知:如何正确求助?哪些是违规求助? 3509667
关于积分的说明 11148111
捐赠科研通 3243362
什么是DOI,文献DOI怎么找? 1792047
邀请新用户注册赠送积分活动 873450
科研通“疑难数据库(出版商)”最低求助积分说明 803801