On the Evolution of Knowledge Graphs: A Survey and Perspective

TL;DR

This paper surveys the evolution of various types of knowledge graphs, their extraction and reasoning techniques, practical applications, and future directions including integration with large language models.

Contribution

It provides a comprehensive overview of knowledge graph types, techniques, applications, and offers perspectives on future research directions and integration with LLMs.

Findings

Different types of KGs have unique evolution paths.

Knowledge extraction and reasoning techniques are advancing rapidly.

Potential of combining KGs with large language models is promising.

Abstract

Knowledge graphs (KGs) are structured representations of diversified knowledge. They are widely used in various intelligent applications. In this article, we provide a comprehensive survey on the evolution of various types of knowledge graphs (i.e., static KGs, dynamic KGs, temporal KGs, and event KGs) and techniques for knowledge extraction and reasoning. Furthermore, we introduce the practical applications of different types of KGs, including a case study in financial analysis. Finally, we propose our perspective on the future directions of knowledge engineering, including the potential of combining the power of knowledge graphs and large language models (LLMs), and the evolution of knowledge extraction, reasoning, and representation.