MetaTKG plus plus : Learning evolving factor enhanced meta-knowledge for temporal knowledge graph reasoning
文献类型：期刊论文
| 作者 | Xia, Yuwei1; Zhang, Mengqi3 ; Liu, Qiang2; Wang, Liang2; Wu, Shu2; Zhang, Xiaoyu1; Wang, Liang2
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2024-11-01 |
| 卷号 | 155页码:12 |
| 关键词 | Knowledge extraction Temporal knowledge graph Meta-learning Evolution pattern |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2024.110629 |
| 通讯作者 | Zhang, Xiaoyu(mengqi.zhang@sdu.edu.cn) |
| 英文摘要 | 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. |
| 资助项目 | National Natural Science Foundation of China (NSFC)[62206291] ; National Natural Science Foundation of China (NSFC)[62376265] ; National Natural Science Foundation of China (NSFC)[62141608] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001251883300001 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | National Natural Science Foundation of China (NSFC) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59017]  |
| 专题 | 多模态人工智能系统全国重点实验室 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Zhang, Xiaoyu |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Cyber Secur, Inst Informat Engn, Beijing, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China 3.Shandong Univ, Jinan, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xia, Yuwei,Zhang, Mengqi,Liu, Qiang,et al. MetaTKG plus plus : Learning evolving factor enhanced meta-knowledge for temporal knowledge graph reasoning[J]. PATTERN RECOGNITION,2024,155:12. |
| APA | Xia, Yuwei.,Zhang, Mengqi.,Liu, Qiang.,Wang, Liang.,Wu, Shu.,...&Wang, Liang.(2024).MetaTKG plus plus : Learning evolving factor enhanced meta-knowledge for temporal knowledge graph reasoning.PATTERN RECOGNITION,155,12. |
| MLA | Xia, Yuwei,et al."MetaTKG plus plus : Learning evolving factor enhanced meta-knowledge for temporal knowledge graph reasoning".PATTERN RECOGNITION 155(2024):12. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。