Affiliations: [a] College of Engineering Pune, Savitribai Phule Pune University, Pune, India | [b] Government College of Engineering and Research, Avasari Khurd, Savitribai Phule Pune University, Pune, India
Correspondence:
[*]
Corresponding author: Anish Rajkumar Khobragade, College of Engineering Pune, Savitribai Phule Pune University, Pune, India. E-mail: [email protected].
Abstract: Knowledge Graph (KG) is the network which contains some topic-based entities, called nodes, and the associated information among the entities. Here, the concept in the knowledge graph is denoted by the tuple relationship, such that the ⟨entity1, predicate, entity2⟩. The entity in the knowledge graph is the abstract concepts based on the particular object, namely the organization, dataset, people, and some associated documentation. The big issue in the KG is that it consists of some incomplete information. The missing details can be identified by employing the knowledge graph completion (KGC) solution. KGC is the same as the link prediction concepts in the knowledge graphs. However, this concept is more complex that it does not predict the link relationship among the nodes but also the diversified information from the link relations. Hence this survey analyzes different methods of link prediction techniques, and this review provides a detailed review of 50 research papers concentrating on various methods, like embedding-based methods, deep learning methods, knowledge acquisition methods, ranking methods, and representation learning methods. The analysis is carried out with respect to the survey based on the publication year, research techniques, performance measures, dataset, toolset and achievement of the research methodologies. Also, the problems in the methods are explained in the research gaps and issues. Furthermore, the future extent of these research works is done based on the limitations identified from the existing research methods.
Keywords: Knowledge graphs, link prediction, representation learning, reasoning and learning, embedding
