CoPE: Composition-based Poincaré embeddings for link prediction in knowledge graphs

Zeb，Adnan1,2; Saif，Summaya3; Chen，Junde4; Yu，James Jianqiao2,5; Jiang，Qingshan6; Zhang，Defu1

2024-03-01

10.1016/j.ins.2024.120197

Information Sciences   影响因子和分区

0020-0255

Knowledge graph (KG) embedding methods predict missing links by computing the similarities between entities. The existing embedding methods are designed with either shallow or deep architectures. Shallow methods are scalable to large KGs but are limited in capturing fine-grained semantics. Deep methods can capture rich semantic interactions, but they require numerous model parameters. This study proposes a novel embedding model that effectively combines the strengths of both shallow and deep models. In particular, the proposed model adopts the design principles of shallow models and incorporates an expressive compositional operator inspired by deep models. This approach maintains the scalability while significantly enhancing the expressive capacity of the proposed model. Moreover, the proposed model learns embeddings using the Poincaré ball model of hyperbolic geometry to preserve the hierarchies between entities. The experimental results demonstrated the effectiveness of learning Poincaré embeddings with an expressive compositional operator. Notably, a substantial improvement of 2.4% in the Mean Reciprocal Rank (MRR) and a 1.4% improvement in hit@1 was observed on the CoDEx-m and CoDEx-s datasets, respectively, when compared to the current state-of-the-art methods. The proposed model was implemented using PyTorch 1.8.1, and experiments were conducted on a server with an NVIDIA GeForce RTX 2080 Ti GPU.

Compositional operators Hyperbolic geometry Knowledge graph Link prediction Poincaré embeddings

SCI ; EI

英语

其他

COMPUTER SCIENCE

2-s2.0-85184025286

Scopus

1.School of Informatics,Xiamen University,Xiamen,Fujian,361005,China
2.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,518000,China
3.Department of Mathematics,COMSATS University,Islamabad,44000,Pakistan
4.Dale E. and Sarah Ann Fowler School of Engineering,Chapman University,United States
5.Department of Computer Science,University of York,York,YO10 5DD,United Kingdom
6.Shenzhen Key Laboratory for High Performance Data Mining,Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,518055,China

Zeb，Adnan,Saif，Summaya,Chen，Junde,et al. CoPE: Composition-based Poincaré embeddings for link prediction in knowledge graphs[J]. Information Sciences,2024,662.

Zeb，Adnan,Saif，Summaya,Chen，Junde,Yu，James Jianqiao,Jiang，Qingshan,&Zhang，Defu.(2024).CoPE: Composition-based Poincaré embeddings for link prediction in knowledge graphs.Information Sciences,662.

Zeb，Adnan,et al."CoPE: Composition-based Poincaré embeddings for link prediction in knowledge graphs".Information Sciences 662(2024).