A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
By Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, Philip S. Yu. 2020
2,800 citations recorded by the source corpus.
Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction toward cognition and human-level intelligence. In this survey, we provide a comprehensive review of the 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 metarelational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of data sets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.
Subfields: Artificial Intelligence, Management Science and Operations Research, Information Extraction, Knowledge Graphs & Representation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Philip S. Yu
- Erik Cambria
- Percy Liang
- Shirui Pan
- Mohit Bansal
- Jianfeng Gao
- Zhiyuan Liu
- Chenguang Zhu
In Management Science and Operations Research
In Information Extraction
In Knowledge Graphs & Representation
Citations in the corpus
- Modifying Memories in Transformer Models (2020, background): “KBs are widely utilized to store and access the relational knowledge in NLP domain (Ji et al., 2020; Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005, inter alia).”
- Knowledge Graphs: Opportunities and Challenges (2023, methodology): “The first task typically adopts link prediction techniques to generate triplets and then assigns the triplets plausibility scores (Ji et al. 2021).”
- A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, positive): “Knowledge graph embedding has great potential on knowledge reasoning [158].”
- A comprehensive review of digital twin — part 1: modeling and twinning enabling technologies (2022, background): “The advantage of ontology in enabling the sharing and reuse of domain knowledge has been one of the key drivers in the recent surge in ontology applications, which has been broadly used in machine learning and information science as a popular means of knowledge representation (Ji et al. 2021).”
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, positive): “A large number of methods are de-velopped to model static KGs without temporally dynamic facts, which have been summarize in recent surveys (Wang et al. 2017; Ji et al. 2020; Dai et al. 2020).”
- Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, background): “More details of knowledge graph embeddings can be found in (Ji et al., 2020; Rossi et al., 2020).”
- On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey (2024, neutral): “For example, we can establish certain links between the LLMs and external knowledge graphs (Ji et al., 2022) or retrieve augmentation from the website (Gao et al., 2023b), which is helpful for the definition, decomposition, and reasoning of data features throughout the entire generation process.”
- A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, methodology): “Prior work such as [4] and [36] also covers the methods for knowledge representation learning and knowledge graph completion, while Cai et al.”
- A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development (2023, background): “To adapt to such changes, one possible approach is to incorporate lifelong learning [124] into the ChatGPT model.”
- A Survey of Knowledge-enhanced Text Generation (2020, methodology): “ly attracted research attention from both academia and industry. A KG is a structured representation of facts (a.k.a. knowledge triplets) consisting of entities†, relations, and semantic descriptions [71]. The terms of knowledge base and knowledge graph are often interchangeably used, but they are n”
- Graph Self-Supervised Learning: A Survey (2021, background): “IN recent years, deep learning on graphs [1], [2], [3], [4] has become increasingly popular for the artificial intelligence research community since graph-structured data is ubiquitous in numerous domains, including e-commerce [5], traffic [6], chemistry [7], and knowledge base [8].”
- Graph Learning: A Survey (2021, background): “Various heterogeneous objects and relationships are regarded as the basis for a knowledge graph [171].”
- Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, background): “KGs are crucial for various applications as they offer accurate explicit knowledge [19].”
- Promises and challenges of generative artificial intelligence for human learning (2024, neutral): “In education, digital twins can simulate real-world scenarios, providing learners with immersive and interactive experiences to enhance understanding and skill development.”
- Domain-specific Knowledge Graphs: A survey (2020, background): “Web data) and other structured or semi-structured sources [6].”