A Survey on Knowledge Graph Embeddings for Link Prediction

Abstract

Knowledge graphs (KGs) have been widely used in the field of artificial intelligence, such as in information retrieval, natural language processing, recommendation systems, etc. However, the open nature of KGs often implies that they are incomplete, having self-defects. This creates the need to build a more complete knowledge graph for enhancing the practical utilization of KGs. Link prediction is a fundamental task in knowledge graph completion that utilizes existing relations to infer new relations so as to build a more complete knowledge graph. Numerous methods have been proposed to perform the link-prediction task based on various representation techniques. Among them, KG-embedding models have significantly advanced the state of the art in the past few years. In this paper, we provide a comprehensive survey on KG-embedding models for link prediction in knowledge graphs. We first provide a theoretical analysis and comparison of existing methods proposed to date for generating KG embedding. Then, we investigate several representative models that are classified into five categories. Finally, we conducted experiments on two benchmark datasets to report comprehensive findings and provide some new insights into the strengths and weaknesses of existing models.

Drug Similarity and Link Prediction Using Graph Embeddings on Medical Knowledge Graphs

“…Embedding learning is an efficient way to tackle data sparseness by representing knowledge graph's entities and relationship as low dimensional real value vectors storing the structural characteristics of the graph structure within themselves [13]. In research [7], the authors have divided the graph embedding models in three families, the first translation distance based which utilizes distance based scoring methods, the second ones are semantic matching based which rely on similarity based scoring methods and finally the third family of neural network based models.…”

“…Driven by the recent 'explosion' of data, many corporations and academic institutions are relying on knowledge graphs for the modelling and analysis of large amounts of data. In this work, we use graph embeddings [7,12] to predict possible relationships between drugs in a drug knowledge base represented as a knowledge graph. Finally, we intend to rely on graph embeddings to provide relevant information and predictions on the given database, as well as to assist us in performing the tasks of relation predictions using link prediction and drug-drug similarity utilising the node similarity concepts mentioned in this work.…”

“…A section of our work inspired from the works like [5] which deals with making inferences using the learned models. The research explore various graph embedding model which has been described and compared in [6], [7] and [8].…”

Graph type expressivity and transformations

“…Knowledge graphs are defined in several ways. In [51], they are defined as heterogeneous directed graphs, while in [60] knowledge graphs are the same as heterogeneous graphs. But there are also definitions that do not see a knowledge graph as a graph, combined from the aforementioned types, see for example [15] for an overview.…”

“…Furthermore, deep learning and data analysis have recently become involved with learning on graph-structured data. Many models have been proposed for learning on different graph types which are collected in various surveys [54,19,25,51]. In contrast to the learning on graphs there are disciplines which use graphs as tool for describing their research objects.…”