Multi-hop path reasoning over sparse temporal knowledge graphs based on path completion and reward shaping

计算机科学 可解释性 知识图 路径(计算) 嵌入 图形 时态数据库 人工智能 时间戳 理论计算机科学 数据挖掘 计算机安全 程序设计语言
作者
Xiangxi Meng,Luyi Bai,Jiahui Hu,Lin Zhu
出处
期刊:Information Processing and Management [Elsevier BV]
卷期号:61 (2): 103605-103605 被引量:31
标识
DOI:10.1016/j.ipm.2023.103605
摘要

Multi-hop path reasoning plays a crucial role in temporal knowledge graph reasoning, aiming to infer deep complex relationships and obtain interpretable reasoning results. Previous reasoning models primarily focus on designing temporal knowledge graphs with rich paths between entities but struggle to handle path sparsity, known as sparse temporal knowledge graphs. Sparse temporal knowledge graphs store only essential knowledge information, resulting in missing connection paths between certain entities and encountering issues of sparse rewards and information scarcity. To tackle these challenges, this paper proposes a multi-hop path reasoning model over sparse temporal knowledge graph based on path completion and reward shaping (STKGR-PR). STKGR-PR dynamically completes missing paths using a temporal embedding model to alleviate path sparsity. To tackle the issue of sparse rewards caused by reduced hit rates, we propose semantic composition-based reasoning path embeddings derived from relation embeddings and timestamp embeddings for reward shaping. Considering the limited information contained in sparse temporal knowledge graphs, we incorporate time vectors into the embedding and multi-hop path reasoning models to enhance the accuracy of reasoning paths and results. Experimental results conducted on six sparse temporal datasets sampled from ICEWS14 and ICEWS515–05 demonstrate that STKGR-PR outperforms state-of-the-art multi-hop path reasoning models over temporal knowledge graphs across all evaluation metrics, while ensuring interpretability.
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
刚刚
1秒前
水煮电吹风的应助被star采纳,获得10
1秒前
2秒前
香蕉觅云的应助被小研家采纳,获得10
3秒前
3秒前
AoGuo发布了新的文献求助10
3秒前
跳跃曼冬发布了新的文献求助10
3秒前
zyz完成签到,获得积分10
3秒前
鹿lu发布了新的文献求助10
3秒前
qingxiao完成签到,获得积分10
3秒前
呀呀完成签到 ,获得积分10
4秒前
4秒前
NexusExplorer的应助被清辉影采纳,获得10
5秒前
千空发布了新的文献求助10
5秒前
6秒前
6秒前
molihuakai的应助被小雨采纳,获得10
8秒前
自信诗桃发布了新的文献求助10
8秒前
铲屎官完成签到,获得积分10
8秒前
9秒前
9秒前
9秒前
无花果的应助被LC2228采纳,获得10
9秒前
Feng完成签到 ,获得积分10
10秒前
耍酷季节的应助被Banana采纳,获得100
10秒前
10秒前
zz不爱读书完成签到,获得积分10
10秒前
11秒前
yi发布了新的文献求助10
11秒前
天天下雨发布了新的文献求助10
11秒前
江亦旋完成签到,获得积分10
11秒前
孟庆亮发布了新的文献求助10
12秒前
曲奇葡萄酒完成签到,获得积分10
12秒前
东城区吴彦祖完成签到,获得积分10
12秒前
13秒前
inRe完成签到,获得积分10
13秒前
13秒前
mlg1552003发布了新的文献求助30
13秒前
碎觉觉发布了新的文献求助30
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183204
求助须知:如何正确求助?哪些是违规求助? 9572434
关于积分的说明 21825655
捐赠科研通 7779988
什么是DOI,文献DOI怎么找? 3433852
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480148