Knowledge graphs are essential and widely used tools in data mining, machine learning, complex networks, and related fields. They represent important entities as nodes and their relationships as edges. In this paper, we conduct a comprehensive review of these graphs and their related methods. We focus on RGNN networks, TDM, and BLM methods, and evaluate their performance and results in depth. This study provides a thorough analysis of the advantages and disadvantages of these methods in dealing with real-world problems and applications. We also present tests on two graphs of biology and general knowledge.
Vahidipour, S. M. , Daneshmand, D. and Zarif, M. A. (2024). An Overview of Embedding Approaches for Knowledge Graphs. Soft Computing Journal, (), -. doi: 10.22052/scj.2024.254464.1224
MLA
Vahidipour, S. M. , , Daneshmand, D. , and Zarif, M. A. . "An Overview of Embedding Approaches for Knowledge Graphs", Soft Computing Journal, , , 2024, -. doi: 10.22052/scj.2024.254464.1224
HARVARD
Vahidipour, S. M., Daneshmand, D., Zarif, M. A. (2024). 'An Overview of Embedding Approaches for Knowledge Graphs', Soft Computing Journal, (), pp. -. doi: 10.22052/scj.2024.254464.1224
CHICAGO
S. M. Vahidipour , D. Daneshmand and M. A. Zarif, "An Overview of Embedding Approaches for Knowledge Graphs," Soft Computing Journal, (2024): -, doi: 10.22052/scj.2024.254464.1224
VANCOUVER
Vahidipour, S. M., Daneshmand, D., Zarif, M. A. An Overview of Embedding Approaches for Knowledge Graphs. Soft Computing Journal, 2024; (): -. doi: 10.22052/scj.2024.254464.1224
)