Modeling Paths and History for Temporal Knowledge Graph Reasoning

计算机科学 推论 加速 人工智能 图形 推理系统 路径(计算) 常识推理 基于模型的推理 机器学习 理论计算机科学 知识表示与推理 程序设计语言 操作系统
作者
Yue Chen,Yongzhong Huang
出处
期刊:Research Square - Research Square
标识
DOI:10.21203/rs.3.rs-4741391/v1
摘要

Abstract Knowledge Graph (KG) reasoning is a crucial task that discovers potential and unknown knowledge based on the existing knowledge. Temporal Knowledge Graph (TKG) reasoning is more challenging than KG reasoning because the additional temporal information needs to be handled. Previous TKG reasoning methods restrict the search space to avoid huge computational consumption, resulting in a decrease in accuracy. In order to improve the accuracy and efficiency of TKG reasoning, a model CMPH (Combination Model of Paths and History) is proposed, which consists of a path memory network and a history memory network. The former finds the paths in advance by a TKG path search algorithm and learns to memorize the recurrent pattern for reasoning, which prevents path search at inference stage. The latter adopts efficient encoder-decoder architecture to learn the features of historical events in TKG, which can avoid tackling a large number of structural dependencies and increase the reasoning accuracy. To take the advantages of these two types of memory networks, a gate component is designed to integrate them for better performance. Extensive experiments on four real-world datasets demonstrate that the proposed model obtains substantial performance and efficiency improvement for the TKG reasoning tasks. Especially, it achieves up to 8.6% and 11.8% improvements in MRR and hit@1 respectively, and up to 21 times speedup at inference stage comparing to the state-of-the-art baseline.
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
1秒前
wanci应助大神水瓶座采纳,获得10
1秒前
1235656646发布了新的文献求助10
1秒前
1秒前
彭洪泽发布了新的文献求助10
2秒前
FashionBoy应助狮子座采纳,获得10
3秒前
思源应助动听的母鸡采纳,获得10
3秒前
3秒前
3秒前
3秒前
爆米花应助俭朴的一曲采纳,获得10
3秒前
4秒前
4秒前
嗯哼发布了新的文献求助10
4秒前
5秒前
ccc完成签到 ,获得积分10
5秒前
阿九发布了新的文献求助10
6秒前
学术学习渣子完成签到,获得积分10
6秒前
Z6kjoA发布了新的文献求助20
6秒前
彭洪泽完成签到,获得积分10
7秒前
7秒前
HAHAHA发布了新的文献求助10
7秒前
刻苦冷菱发布了新的文献求助10
7秒前
7秒前
7秒前
8秒前
1235656646完成签到,获得积分10
8秒前
tyZhang完成签到,获得积分10
8秒前
纯真冰露完成签到,获得积分10
8秒前
清爽源智完成签到,获得积分10
8秒前
xxj发布了新的文献求助30
9秒前
Zsx完成签到,获得积分10
10秒前
10秒前
starryxm完成签到,获得积分10
10秒前
10秒前
雷锋完成签到,获得积分10
10秒前
清爽源智发布了新的文献求助10
11秒前
11秒前
Qing灿完成签到,获得积分10
12秒前
Q Eason发布了新的文献求助10
12秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3988732
求助须知:如何正确求助?哪些是违规求助? 3531027
关于积分的说明 11252281
捐赠科研通 3269732
什么是DOI,文献DOI怎么找? 1804764
邀请新用户注册赠送积分活动 881869
科研通“疑难数据库(出版商)”最低求助积分说明 809021