Missing relation prediction in knowledge graph using local and neighbour aware entity embedding

Khobragade, Anish; Patil, Sanket; Rathi, Harsha; Ghumbre, Shashikant

doi:10.47974/JDMSC-1972

Open Access Research Article

Missing relation prediction in knowledge graph using local and neighbour aware entity embedding

^*Anish KhobragadeCorresponding authoranishraj.comp@coeptech.ac.inDepartment of Computer Science and EngineeringCOEP Technological UniversityPune, Maharashtra, 411005, IndiaView full profile → , Sanket Patilpatilsr18.comp@coep.ac.inDepartment of Computer Science and EngineeringCOEP Technological UniversityPune, Maharashtra, 411005, IndiaView full profile → , Harsha Rathirathihs18.comp@coep.ac.inDepartment of Computer Science and EngineeringCOEP Technological UniversityPune, Maharashtra, 411005, IndiaView full profile → , Shashikant Ghumbreshashi.ghumbre@gmail.comDepartment of Computer EngineeringGovernment College of Engineering and Research, Avasari KhurdPune, Maharashtra, 412405, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 1173–1184Vol. 27Issue 4June 2024DOI: 10.47974/JDMSC-1972 Crossmark XML

Published Online:: 26 Jun 2024
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-1972
Pages:: 1173–1184

Abstract

Predicting relations involves deducing the absent connections between entities within a knowledge graph. Knowledge graph embedding has recently emerged as a technique to represent entities and their relationships in a condensed vector space. While effective for entity prediction tasks, this approach escalates in complexity, particularly for extensive knowledge graphs. This study introduces a new method for relation prediction in knowledge graphs, employing a mechanism termed Local and Neighbor Aware Entity Embedding (LNAEE). LNAEE utilizes skip-gram initialization to capture local entity features at the triple level. It then employs an attention mechanism to update the central entity’s features based on its immediate neighbors. Finally, a multilayer neural network predicts the most likely relationship type between the given entity pair. LNAEE is streamlined and less intricate owing to the reduced relation search space. Benchmark dataset experiments demonstrate that LNAEE outperforms the baselines. This makes LNAEE ideal for applications requiring a lightweight and affordable model for knowledge graph enrichment.

Keywords

Knowledge graph Representation learning Embedding Relation prediction Attention network

Subject Classifications

Primary 68T35Secondary 68T05

References

[1] A. Khobragade and S. Ghumbre, Study and analysis of various link predictions in knowledge graph: A challenging overview, Intelligent Decision Technologies, 16. 4, 653-663, (2022).
[2] H. Nguyen, et al., Design an ontology model for intelligent querying system in mathematics education, Journal of Inter. Math., 26.3, 449-473, (2023).
[3] R. C. Poonia, et al., “Face Recognition System for Medical Information Modeling Using Machine Learning.” In Handbook of Research on Mathematical Modeling for Smart Healthcare Systems, pp. 353-373. IGI Global, (2022).
[4] A. Kumar, et al., “An enhanced quantum key distribution protocol for security authentication.” Journal of Discrete Mathematical Sciences and Cryptography 22, no. 4 (2019).
[5] A. Kumar, et al., “An improved quantum key distribution protocol for verification.” Journal of Discrete Mathematical Sciences and Cryptography 22, no. 4 (2019).
[6] A. Bordes, et al., Translating embeddings for modeling multi-relational data, In Proceeding of Advances in NLPS, (2013).
[7] W. Zhen, J. Zhang, J. Feng and Z. Chen, Knowledge graph embedding by translating on hyperplanes, In Proceedings of the AAAI, (2014).
[8] L. Yankai, et al., Learning entity and relation embeddings for knowledge graph completion, In Proceedings of the AAAI, (2015).
[9] J. Guoliang, S. He, L. Xu, K. Liu and J. Zhao, Knowledge graph embedding via dynamic mapping matrix, In Procedings of the ACL, (2015).
[10] D. Song, et al., DTransE: Distributed translating embedding for knowledge graph, IEEE Trans. on Para. and Distr. Syst., 32.10, 2509-2523, (2021).
[11] Y. Bishan, et al., Embedding entities and relations for learning and inference in knowledge bases, In Procceding of ICLR, (2015).
[12] T. Théo, et al., Complex embeddings for simple link prediction, In Proceeding of the ICML, (2016).
[13] N. Maximilian, L. Rosasco and T. Poggio, Holographic embeddings of knowledge graphs, In Proceedings of the AAAI, (2016).
[14] D. Tim, et al., Convolutional 2d knowledge graph embeddings, In Proceedings of the AAAI, (2018).
[15] N. D. Quoc, et al., A novel embedding model for knowledge base completion based on convolutional neural network, In Proceeding of NAACL, (2018).
[16] J. Xiaotian, Q. Wang and B. Wang, Adaptive convolution for multi-relational learning, In Proceedings of NAACL, (2019).
[17] A. khobragade, S. Ghumbre and F. Wangde, Convolutional neural network for knowledge graph completion, AIP Conference Proceedings, (2023).
[18] M. Tomas, et al., Distributed representations of words and phrases and their compositionality, In Proceeding of the Adance NLPS, (2013).
[19] A. Khobragade, et al., Effective negative triplet sampling for knowledge graph embedding, Jour. Info. and Optim. Sci., 43.8, 2075-2087, (2022).

Views: 516Downloads: 78Citations: 0