A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

Abstract

Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review of knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed. We further explore several emerging topics, including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

STonKGs: A Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs

“…Given the complexity of biological scientific literature, the contextual representations learned by STonKGs could benefit from longer sequences (i.e., the context of a given triple is often mentioned in the surrounding sentences). Thirdly, while we have generated the node embeddings based on node2vec, other more sophisticated models such as Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) (Ji et al, 2021) could be employed. However, this is practically infeasible due to the computational complexity required given the size of our KG.…”

“…Knowledge graphs (KGs) represent information in a structured manner in order to encode the broad spectrum of complex interactions occurring in biology. In order to exploit the information contained in KGs through machine learning algorithms, numerous knowledge graph embedding models (KGEMs) have been developed to encode the entities and relations of KGs in a higher dimensional vector space while attempting to retain their structural properties (Ji et al, 2021). Utilizing the resulting vector representations, more sophisticated tasks can be conducted (i.e., link prediction, node classification, and graph classification).…”

Knowledge Graphs Representation for Event-Related E-News Articles

“…Fifteen years ago, researchers at the University of Twente and the University of Groningen, Netherlands, initiated the researches on KG theory and continued its focus on KG applications to analyze a text [5]. Over the years, several open KBs or ontologies have been created, including WordNet, DBpedia, YAGO, Freebase, BabelNet, and NELL, covering millions of real-world entities and relations in different domains [3,10,11,13]. Among these, traditional KGs such as ConceptNet and Freebase usually contain known facts and assertions about entities [12].…”

“…YAGO is another open-sourced semantic KG resultant from Wikipedia and WordNet, which has more than 10 million entities and 120 million entity links. The concept of KG expanded its popularity in 2012 with the first KG known as the 'Knowledge Vault', launched by Google's search engine, which is a knowledge fusion framework that was proposed to build large-scale KGs [10]. The potential data requirement of such well-constructed largescale KGs is much larger but can be advantageous for many applications.…”

Deep Graph Generators: A Survey

“…Related works. So far, several surveys have reviewed deep graph-related approaches such as those mainly focusing on graph representation learning methods [6], [72]- [78], graph attention models [79], knowledge graph research [80], [81], attack and defense techniques on graph data [82], and graph matching approaches [83], [84]. Although most of these surveys have made a passing reference to some modern graph generators, this field requires individual attention due to its value and growing popularity.…”