Knowledge Graph Embedding Using a Multi-Channel Interactive Convolutional Neural Network with Triple Attention
-
Published:2024-09-11
Issue:18
Volume:12
Page:2821
-
ISSN:2227-7390
-
Container-title:Mathematics
-
language:en
-
Short-container-title:Mathematics
Author:
Shi Lin1, Liu Weitao1, Wu Yafeng1, Dai Chenxu1, Ji Zhanlin23ORCID, Ganchev Ivan345ORCID
Affiliation:
1. Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China 2. College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China 3. Telecommunications Research Centre (TRC), University of Limerick, V94 T9PX Limerick, Ireland 4. Department of Computer Systems, University of Plovdiv “Paisii Hilendarski”, 4000 Plovdiv, Bulgaria 5. Institute of Mathematics and Informatics—Bulgarian Academy of Sciences, 1040 Sofia, Bulgaria
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.
Reference39 articles.
1. Saxena, S., Sangani, R., Prasad, S., Kumar, S., Athale, M., Awhad, R., and Vaddina, V. (2022, January 17–20). Large-Scale Knowledge Synthesis and Complex Information Retrieval from Biomedical Documents. Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan. 2. A Diagrammatic Approach for Visual Question Answering over Knowledge Graphs;Gangemi;The Semantic Web: ESWC 2018 Satellite Events, Proceedings of the 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, 3–7 June 2018,2018 3. Suchanek, F.M., Kasneci, G., and Weikum, G. (2007, January 8–12). Yago: A Core of Semantic Knowledge. Proceedings of the 16th International Conference on World Wide Web, Banff, AB, Canada. 4. Bollacker, K., Evans, C., Paritosh, P., Sturge, T., and Taylor, J. (2018, January 9–12). Freebase: A Collaboratively Created Graph Database for Structuring Human Knowledge. Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, Vancouver, BC, Canada. 5. Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., and Ives, Z. (2007, January 11–15). Dbpedia: A Nucleus for a Web of Open Data. Proceedings of the International Semantic Web Confermahdisoltani, Busan, Republic of Korea.
|
|