CASIA OpenIR  > 模式识别实验室
MetaTKG++: Learning Evolving Factor Enhanced Meta-knowledge for Temporal Knowledge Graph Reasoning
Yuwei Xia; Mengqi Zhang; Qiang Liu; Liang Wang; Shu Wu; Xiaoyu Zhang; Liang Wang
发表期刊PATTERN RECOGNITION
2024
卷号155页码:1-12
文章类型期刊论文(录用)
摘要

Reasoning over Temporal Knowledge Graphs (TKGs) aims to predict future facts based on the given history. One of the key challenges for prediction is to analyze the evolution process of facts. Most existing works focus on exploring evolutionary information in history to obtain effective temporal embeddings for entities and relations, but they ignore the variation in evolution patterns of facts caused by numerous diverse entities and latent evolving factors, which makes them struggle to adapt to future data with different evolution patterns. Moreover, new entities continue to emerge along with the evolution of facts over time. Since existing models highly rely on historical information to learn embeddings for entities, they perform poorly on such entities with little historical information. To tackle these issues, we propose a novel evolving factor enhanced temporal meta-learner framework for TKG reasoning, MetaTKG++ for brevity. Specifically, we first propose a temporal meta-learner which regards TKG reasoning as many temporal meta-tasks for training. From the training process of each meta-task, the obtained meta-knowledge can guide backbones to adapt to future data exhibiting various evolution patterns and to effectively learn entities with little historical information. Then, we design an Evolving Factor Learning module, which aims to assist backbones in learning evolution patterns by modeling latent evolving factors. Meanwhile, during the training process with the proposed meta-learner, the learnable evolving factor can enhance the meta-knowledge with providing more comprehensive information on learning evolution patterns. Extensive experiments on five widely-used datasets and four backbones demonstrate that our method can greatly improve the performance on TKG prediction.

七大方向——子方向分类模式识别基础
国重实验室规划方向分类智能计算与学习
是否有论文关联数据集需要存交
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/57489
专题模式识别实验室
通讯作者Shu Wu
作者单位1.中国科学院自动化研究所
2.中国科学院信息工程研究所
推荐引用方式
GB/T 7714
Yuwei Xia,Mengqi Zhang,Qiang Liu,et al. MetaTKG++: Learning Evolving Factor Enhanced Meta-knowledge for Temporal Knowledge Graph Reasoning[J]. PATTERN RECOGNITION,2024,155:1-12.
APA Yuwei Xia.,Mengqi Zhang.,Qiang Liu.,Liang Wang.,Shu Wu.,...&Liang Wang.(2024).MetaTKG++: Learning Evolving Factor Enhanced Meta-knowledge for Temporal Knowledge Graph Reasoning.PATTERN RECOGNITION,155,1-12.
MLA Yuwei Xia,et al."MetaTKG++: Learning Evolving Factor Enhanced Meta-knowledge for Temporal Knowledge Graph Reasoning".PATTERN RECOGNITION 155(2024):1-12.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yuwei Xia]的文章
[Mengqi Zhang]的文章
[Qiang Liu]的文章
百度学术
百度学术中相似的文章
[Yuwei Xia]的文章
[Mengqi Zhang]的文章
[Qiang Liu]的文章
必应学术
必应学术中相似的文章
[Yuwei Xia]的文章
[Mengqi Zhang]的文章
[Qiang Liu]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。