Saved in:
Bibliographic Details
Main Authors: Ying, Rui, Hu, Mengting, Wu, Jianfeng, Xie, Yalan, Liu, Xiaoyi, Wang, Zhunheng, Jiang, Ming, Gao, Hang, Zhang, Linlin, Cheng, Renhong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.06603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929457559764992
author Ying, Rui
Hu, Mengting
Wu, Jianfeng
Xie, Yalan
Liu, Xiaoyi
Wang, Zhunheng
Jiang, Ming
Gao, Hang
Zhang, Linlin
Cheng, Renhong
author_facet Ying, Rui
Hu, Mengting
Wu, Jianfeng
Xie, Yalan
Liu, Xiaoyi
Wang, Zhunheng
Jiang, Ming
Gao, Hang
Zhang, Linlin
Cheng, Renhong
contents Temporal knowledge graph completion aims to infer the missing facts in temporal knowledge graphs. Current approaches usually embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs. However, these methods only adopt a single operation, which may have limitations in capturing the complex temporal dynamics present in temporal knowledge graphs. Therefore, we propose a simple but effective method, i.e. TCompoundE, which is specially designed with two geometric operations, including time-specific and relation-specific operations. We provide mathematical proofs to demonstrate the ability of TCompoundE to encode various relation patterns. Experimental results show that our proposed model significantly outperforms existing temporal knowledge graph embedding models. Our code is available at https://github.com/nk-ruiying/TCompoundE.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06603
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion
Ying, Rui
Hu, Mengting
Wu, Jianfeng
Xie, Yalan
Liu, Xiaoyi
Wang, Zhunheng
Jiang, Ming
Gao, Hang
Zhang, Linlin
Cheng, Renhong
Artificial Intelligence
Temporal knowledge graph completion aims to infer the missing facts in temporal knowledge graphs. Current approaches usually embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs. However, these methods only adopt a single operation, which may have limitations in capturing the complex temporal dynamics present in temporal knowledge graphs. Therefore, we propose a simple but effective method, i.e. TCompoundE, which is specially designed with two geometric operations, including time-specific and relation-specific operations. We provide mathematical proofs to demonstrate the ability of TCompoundE to encode various relation patterns. Experimental results show that our proposed model significantly outperforms existing temporal knowledge graph embedding models. Our code is available at https://github.com/nk-ruiying/TCompoundE.
title Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion
topic Artificial Intelligence
url https://arxiv.org/abs/2408.06603