Symbolic Knowledge Reasoning on Hyper-Relational Knowledge Graphs
Zikang Wang; Linjing Li; Daniel Zeng
发表期刊IEEE Transactions on Big Data
2024
页码accept
摘要

Knowledge reasoning has been widely researched in knowledge graphs (KGs), but there has been relatively less research on hyper-relational KGs, which also plays an important role in downstream tasks. Existing reasoning methods on hyper-relational KGs are based on representation learning. Though this approach is effective, it lacks interpretability and ignores the graph structure information. In this paper, we make the first attempt at symbolic reasoning on hyper-relational KGs. We introduce rule extraction methods based on both individual facts and paths, and propose a rule-based symbolic reasoning approach, HyperPath. This approach is simple and interpretable, it can serve as a baseline model for symbolic reasoning in hyper-relational KGs. We provide experimental results on almost all datasets, including five large-scale datasets and seven sub-datasets of them. Experiments show that the expressive power of the proposed model is similar to simple neural networks like convolutional networks, but not as advanced as more complex networks such as Transformer and graph convolutional networks, which is consistent with the performance of symbolic methods on KGs. Furthermore, we also analyze the impact of rule length and hyperparameters on the model's performance, which can provide insights for future research in hypergraph symbolic reasoning. The code is available at https://github.com/von1000/HyperPath.

关键词hyper-relational knowledge graph, knowledge reasoning, multi-hop reasoning
收录类别SCI
七大方向——子方向分类知识表示与推理
国重实验室规划方向分类复杂系统建模与推演
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/173211/57437
专题舆论大数据科学与技术应用联合实验室
通讯作者Zikang Wang
作者单位Institute of Automation, Chinese Academy of Sciences
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zikang Wang,Linjing Li,Daniel Zeng. Symbolic Knowledge Reasoning on Hyper-Relational Knowledge Graphs[J]. IEEE Transactions on Big Data,2024:accept.
APA Zikang Wang,Linjing Li,&Daniel Zeng.(2024).Symbolic Knowledge Reasoning on Hyper-Relational Knowledge Graphs.IEEE Transactions on Big Data,accept.
MLA Zikang Wang,et al."Symbolic Knowledge Reasoning on Hyper-Relational Knowledge Graphs".IEEE Transactions on Big Data (2024):accept.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
paper.pdf(4767KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Zikang Wang]的文章
[Linjing Li]的文章
[Daniel Zeng]的文章
百度学术
百度学术中相似的文章
[Zikang Wang]的文章
[Linjing Li]的文章
[Daniel Zeng]的文章
必应学术
必应学术中相似的文章
[Zikang Wang]的文章
[Linjing Li]的文章
[Daniel Zeng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: paper.pdf
格式: Adobe PDF
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。