A Neighborhood-Aware Graph Self-Attention Mechanism-based Pre-Training Model for Knowledge Graph Reasoning

推论 计算机科学 图形 编码 人工智能 数据挖掘 模式识别(心理学) 机器学习 理论计算机科学 数学 生物化学 基因 化学
作者
Yuejia Wu,Jian-tao Zhou
出处
期刊:Information Sciences [Elsevier BV]
卷期号:647: 119473-119473
标识
DOI:10.1016/j.ins.2023.119473
摘要

Knowledge Graph Reasoning (KGR) is an effective method to ameliorate incompleteness and sparsity problems, which infers new knowledge based on existing knowledge. The Graph Neural Network (GNN)-based approaches can obtain advanced effectiveness. However, it still suffers from some problems such as obtaining insufficient graph features, introducing noises, ignoring path connectivity, and acquiring incomplete neighborhood information. This paper proposes a neighborhood-aware (NA) graph self-attention mechanism-based pre-training model for KGR, namely NA-KGR. The proposed model is composed of two phases. The first phase is an enhanced graph attention network, which can use the weighted characteristics of its neighbors to represent and encode the entities that are most likely to have a positive effect on reasoning. The second phase is a neighborhood-aware self-attention mechanism, which makes the model more able to obtain information from the neighbor entities for inference by increasing an adaptive entity similarity matrix when calculating the attention score. Moreover, we propose a pre-training pattern based on neighborhood-aware random walk sampling and general subgraph structure sampling to improve NA-KGR's generalization ability. Extensive comparison and ablation experimental results on various benchmarks unambiguously demonstrate that the proposed NA-KGR model can obtain the state-of-the-art results of current GNN-based methods.
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
Mm林完成签到,获得积分10
刚刚
我就是我完成签到,获得积分10
刚刚
盈滢完成签到 ,获得积分10
刚刚
Jay_Gavin应助白白采纳,获得10
1秒前
zy发布了新的文献求助10
2秒前
Liang发布了新的文献求助10
2秒前
美丽的楼房完成签到 ,获得积分10
4秒前
4秒前
大观天下完成签到,获得积分10
5秒前
端庄的冬天完成签到,获得积分10
5秒前
所所应助yizhe采纳,获得10
5秒前
高大的静曼完成签到,获得积分10
6秒前
JK完成签到,获得积分10
7秒前
景行行止完成签到,获得积分10
7秒前
草原狼完成签到,获得积分10
7秒前
7秒前
gexiaoyang完成签到 ,获得积分10
8秒前
量子星尘发布了新的文献求助10
9秒前
小二郎应助自信的孱采纳,获得10
9秒前
小马甲应助小王采纳,获得10
10秒前
伶俐的秋白完成签到,获得积分10
10秒前
10秒前
思源应助维生素采纳,获得10
11秒前
11秒前
完美梨愁发布了新的文献求助10
14秒前
14秒前
15秒前
英俊的铭应助白兰鸽采纳,获得10
17秒前
布洛小芬完成签到 ,获得积分20
18秒前
whatever应助shark采纳,获得20
18秒前
默默雪旋完成签到 ,获得积分10
18秒前
牧紫菱完成签到,获得积分10
19秒前
20秒前
21秒前
小王发布了新的文献求助10
21秒前
21秒前
Eric完成签到,获得积分10
22秒前
开朗的山彤完成签到,获得积分10
22秒前
维生素完成签到,获得积分10
22秒前
时林完成签到,获得积分10
22秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 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 4038388
求助须知:如何正确求助?哪些是违规求助? 3576106
关于积分的说明 11374447
捐赠科研通 3305798
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029