Knowledge Graph Embedding Using a Multi-Channel Interactive Convolutional Neural Network with Triple Attention

Lin Shi, Weitao Liu, Yafeng Wu, Chenxu Dai, Zhanlin Ji () and Ivan Ganchev ()
Additional contact information
Lin Shi: Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
Weitao Liu: Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
Yafeng Wu: Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
Chenxu Dai: Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
Zhanlin Ji: College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China
Ivan Ganchev: Telecommunications Research Centre (TRC), University of Limerick, V94 T9PX Limerick, Ireland

Mathematics, 2024, vol. 12, issue 18, 1-20

Abstract: Knowledge graph embedding (KGE) has been identified as an effective method for link prediction, which involves predicting missing relations or entities based on existing entities or relations. KGE is an important method for implementing knowledge representation and, as such, has been widely used in driving intelligent applications w.r.t. question-answering systems, recommendation systems, and relationship extraction. Models based on convolutional neural networks (CNNs) have achieved good results in link prediction. However, as the coverage areas of knowledge graphs expand, the increasing volume of information significantly limits the performance of these models. This article introduces a triple-attention-based multi-channel CNN model, named ConvAMC, for the KGE task. In the embedding representation module, entities and relations are embedded into a complex space and the embeddings are performed in an alternating pattern. This approach helps in capturing richer semantic information and enhances the expressive power of the model. In the encoding module, a multi-channel approach is employed to extract more comprehensive interaction features. A triple attention mechanism and max pooling layers are used to ensure that interactions between spatial dimensions and output tensors are captured during the subsequent tensor concatenation and reshaping process, which allows preserving local and detailed information. Finally, feature vectors are transformed into prediction targets for embedding through the Hadamard product of feature mapping and reshaping matrices. Extensive experiments were conducted to evaluate the performance of ConvAMC on three benchmark datasets compared with state-of-the-art (SOTA) models, demonstrating that the proposed model outperforms all compared models across all evaluation metrics on two of the datasets, and achieves advanced link prediction results on most evaluation metrics on the third dataset.

Keywords: knowledge graph embedding (KGE); link prediction; convolutional neural network (CNN); multi-channel convolution; triple attention (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/18/2821/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/18/2821/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:18:p:2821-:d:1476178

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().