Knowledge graph explained

In knowledge representation and reasoning, a knowledge graph is a knowledge base that uses a graph-structured data model or topology to represent and operate on data. Knowledge graphs are often used to store interlinked descriptions of entities objects, events, situations or abstract concepts while also encoding the free-form semantics or relationships underlying these entities.[1] [2]

Since the development of the Semantic Web, knowledge graphs have often been associated with linked open data projects, focusing on the connections between concepts and entities.[3] [4] They are also historically associated with and used by search engines such as Google, Bing, and Yahoo; knowledge engines and question-answering services such as WolframAlpha, Apple's Siri, and Amazon Alexa; and social networks such as LinkedIn and Facebook.

Recent developments in data science and machine learning, particularly in graph neural networks and representation learning and also in machine learning, have broadened the scope of knowledge graphs beyond their traditional use in search engines and recommender systems. They are increasingly used in scientific research, with notable applications in fields such as genomics, proteomics, and systems biology.[5]

History

The term was coined as early as 1972 by the Austrian linguist Edgar W. Schneider, in a discussion of how to build modular instructional systems for courses.[6] In the late 1980s, the University of Groningen and University of Twente jointly began a project called Knowledge Graphs, focusing on the design of semantic networks with edges restricted to a limited set of relations, to facilitate algebras on the graph.[7] In subsequent decades, the distinction between semantic networks and knowledge graphs was blurred.

Some early knowledge graphs were topic-specific. In 1985, Wordnet was founded, capturing semantic relationships between words and meanings an application of this idea to language itself. In 2005, Marc Wirk founded Geonames to capture relationships between different geographic names and locales and associated entities. In 1998 Andrew Edmonds of Science in Finance Ltd in the UK created a system called ThinkBase that offered fuzzy-logic based reasoning in a graphical context.[8]

In 2007, both DBpedia and Freebase were founded as graph-based knowledge repositories for general-purpose knowledge.[9] DBpedia focused exclusively on data extracted from Wikipedia, while Freebase also included a range of public datasets. Neither described themselves as a 'knowledge graph' but developed and described related concepts.

In 2012, Google introduced their Knowledge Graph,[10] building on DBpedia and Freebase among other sources. They later incorporated RDFa, Microdata, JSON-LD content extracted from indexed web pages, including the CIA World Factbook, Wikidata, and Wikipedia.[11] Entity and relationship types associated with this knowledge graph have been further organized using terms from the schema.org[12] vocabulary. The Google Knowledge Graph became a successful complement to string-based search within Google, and its popularity online brought the term into more common use.

Since then, several large multinationals have advertised their knowledge graphs use, further popularising the term. These include Facebook, LinkedIn, Airbnb, Microsoft, Amazon, Uber and eBay.[13]

In 2019, IEEE combined its annual international conferences on "Big Knowledge" and "Data Mining and Intelligent Computing" into the International Conference on Knowledge Graph.[14]

The development of large language models expanded interest in knowledge graphs as a way to structure information from unstructured text, with advances in language processing enabling their automatic or semi-automatic generation and expansion.[15] [16] The term knowledge graph has since broadened to include the dynamically constructed and adaptive graph structures, which support retrieval, reasoning, and summarization in generative systems. Microsoft Research’s GraphRAG (2024) exemplified this development by integrating LLM-generated graphs into retrieval-augmented generation.

Definitions

There is no single commonly accepted definition of a knowledge graph. Most definitions view the topic through a Semantic Web lens and include these features:[17]

There are, however, many knowledge graph representations for which some of these features are not relevant. For those knowledge graphs, this simpler definition may be more useful:

Implementations

In addition to the above examples, the term has been used to describe open knowledge projects such as YAGO and Wikidata; federations like the Linked Open Data cloud;[23] a range of commercial search tools, including Yahoo's semantic search assistant Spark, Google's Knowledge Graph, and Microsoft's Satori; and the LinkedIn and Facebook entity graphs.

The term is also used in the context of note-taking software applications that allow a user to build a personal knowledge graph.[24]

The popularization of knowledge graphs and their accompanying methods have led to the development of graph databases such as Neo4j,[25] GraphDB[26] and AgensGraph.[27] These graph databases allow users to easily store data as entities and their interrelationships, and facilitate operations such as data reasoning, node embedding, and ontology development on knowledge bases.

In contrast, virtual knowledge graphs do not store information in specialized databases.[28] They rely on an underlying relational database or data lake to answer queries on the graph. Such a virtual knowledge graph system must be properly configured in order to answer the queries correctly. This specific configuration is done through a set of mappings that define the relationship between the elements of the data source and the structure and ontology of the virtual knowledge graph.[29]

Using a knowledge graph for reasoning over data

See main article: Ontology (information science).

A knowledge graph formally represents semantics by describing entities and their relationships.[30] Knowledge graphs may make use of ontologies as a schema layer. By doing this, they allow logical inference for retrieving implicit knowledge rather than only allowing queries requesting explicit knowledge.[31]

In order to allow the use of knowledge graphs in various machine learning tasks, several methods for deriving latent feature representations of entities and relations have been devised.[32] These knowledge graph embeddings allow them to be connected to machine learning methods that require feature vectors like word embeddings. This can complement other estimates of conceptual similarity.[33]

Models for generating useful knowledge graph embeddings are commonly the domain of graph neural networks (GNNs).[34] GNNs are deep learning architectures that comprise edges and nodes, which correspond well to the entities and relationships of knowledge graphs. The topology and data structures afforded by GNNs provide a convenient domain for semi-supervised learning, wherein the network is trained to predict the value of a node embedding (provided a group of adjacent nodes and their edges) or edge (provided a pair of nodes). These tasks serve as fundamental abstractions for more complex tasks such as knowledge graph reasoning and alignment.[35]

Entity alignment

As new knowledge graphs are produced across a variety of fields and contexts, the same entity will inevitably be represented in multiple graphs. However, because no single standard for the construction or representation of knowledge graph exists, resolving which entities from disparate graphs correspond to the same real world subject is a non-trivial task. This task is known as knowledge graph entity alignment, and is an active area of research.[36]

Strategies for entity alignment generally seek to identify similar substructures, semantic relationships, shared attributes, or combinations of all three between two distinct knowledge graphs.[37] Entity alignment methods use these structural similarities between generally non-isomorphic graphs to predict which nodes corresponds to the same entity.[38]

The recent successes of large language models (LLMs), in particular their effectiveness at producing syntactically meaningful embeddings, has spurred the use of LLMs in the task of entity alignment.[39]

As the amount of data stored in knowledge graphs grows, developing dependable methods for knowledge graph entity alignment becomes an increasingly crucial step in the integration and cohesion of knowledge graph data.

See also

External links

Notes and References

  1. Web site: 2018 . What is a Knowledge Graph? . 2025-12-05 . ontotext.
  2. Web site: Kumar Pandey . Atul . 2020-12-18 . What defines a knowledge graph? . 2025-12-05 . AtulHost.
  3. Ehrlinger. Lisa. Wöß. Wolfram. 2016. Towards a Definition of Knowledge Graphs. SEMANTiCS2016. Leipzig. Joint Proceedings of the Posters and Demos Track of 12th International Conference on Semantic Systems – SEMANTiCS2016 and 1st International Workshop on Semantic Change & Evolving Semantics (SuCCESS16). 13–16.
  4. Book: Soylu, Ahmet. The Semantic Web – ISWC 2020 . Enhancing Public Procurement in the European Union Through Constructing and Exploiting an Integrated Knowledge Graph . 2020. https://doi.org/10.1007/978-3-030-62466-8_27. Lecture Notes in Computer Science. 12507. en. 430–446. 10.1007/978-3-030-62466-8_27. 978-3-030-62465-1. 226229398.
  5. Mohamed . Sameh K. . Nounu . Aayah . Nováček . Vít . 2021 . Biological applications of knowledge graph embedding models . Briefings in Bioinformatics . 22 . 2 . 1679–1693 . 10.1093/bib/bbaa012 . 32065227 . Oxford Academic. free . 1983/919db5c6-6e10-4277-9ff9-f86bbcedcee8 . free .
  6. Web site: Schneider . Edward W. . 1973 . Course Modularization Applied: The Interface System and Its Implications For Sequence Control and Data Analysis. . 5 December 2025.
  7. Victor . Filippov . Natalya . Ayusheeva . Maria . Kusheeva . 2024-03-17 . Algorithms and methods for automated construction of knowledge graphs based on text sources . 2025-08-18 . E3S Web of Conferences . 531 . 03017 . 10.1051/e3sconf/202453103017 . 2024E3SWC.53103017F .
  8. Web site: US Trademark no 75589756 . dead.
  9. Web site: Michael . Färber . Basil . Ell . Carsten . Menne . Achim . Rettinger . 2015-01-15 . A Comparative Survey of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO . 2025-08-18 . KIT.
  10. Web site: Singhal. Amit. May 16, 2012. Introducing the Knowledge Graph: things, not strings. 21 March 2017. Official Google Blog.
  11. Web site: Schwartz. Barry. December 17, 2014. Google's Freebase To Close After Migrating To Wikidata: Knowledge Graph Impact?. December 10, 2017. Search Engine Roundtable.
  12. Web site: McCusker. James P.. McGuiness. Deborah L.. What is a Knowledge Graph?. 21 March 2017. www.authorea.com.
  13. Web site: 2020 . Knowledge Graph Enterprises . dead.
  14. Web site: 2017-07-09. 2021 IEEE International Conference on Knowledge Graph (ICKG)*. 2021-03-22. KMedu Hub. en-US.
  15. Book: Yih . Wen-tau . Chang . Ming-Wei . He . Xiaodong . Gao . Jianfeng . Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base . July 2015 . Zong . Chengqing . Strube . Michael . Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) . https://aclanthology.org/P15-1128/ . Beijing, China . Association for Computational Linguistics . 1321–1331 . 10.3115/v1/P15-1128.
  16. Lewis . Patrick . Perez . Ethan . Piktus . Aleksandra . Petroni . Fabio . Karpukhin . Vladimir . Goyal . Naman . Küttler . Heinrich . Lewis . Mike . Yih . Wen-tau . Rocktäschel . Tim . Riedel . Sebastian . Kiela . Douwe . 2020 . Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks . Advances in Neural Information Processing Systems . Curran Associates, Inc. . 33 . 9459–9474.
  17. Hogan. Aidan. Blomqvist. Eva. Cochez. Michael. d'Amato. Claudia. de Melo. Gerard. Gutierrez. Claudio. Labra Gayo. José Emilio. Kirrane. Sabrina. Neumaier. Sebastian. Polleres. Axel. Navigli. Roberto. Ngonga Ngomo. Axel-Cyrille. Rashid. Sabbir M.. Rula. Anisa. Schmelzeisen. Lukas. Sequeda. Juan. Staab. Steffen. Zimmermann. Antoine. 2021-01-24. Knowledge Graphs. ACM Computing Surveys. 54. 4. 1–37. 10.1145/3447772. 0360-0300. 2003.02320. 235716181.
  18. Paulheim. Heiko. 2017. Knowledge Graph Refinement: A Survey of Approaches and Evaluation Methods. Semantic Web. 489–508. 21 March 2017.
  19. Krötsch. Markus. Weikum. Gerhard. Editorial of the Special Issue on Knowledge Graphs. Journal of Web Semantics. March 2016. 37-38. 53–54. 10.1016/j.websem.2016.04.002. 10 February 2021. subscription.
  20. Web site: What is a Knowledge Graph?Ontotext. 2020-07-01. Ontotext. en-US.
  21. Peng. Ciyuan. Feng. Xia. Naseriparsa. Mehdi. Osborne. Francesco. 2023. Knowledge Graphs: Opportunities and Challenges. Artificial Intelligence Review. 56. 11 . 13071–13102. 10.1007/s10462-023-10465-9. 37362886 . 10068207 . 1573-7462. 2303.13948.
  22. Web site: 2020. The Knowledge Graph about Knowledge Graphs. dead. https://web.archive.org/web/20200717054553/https://kgkg.factnexus.com/@3782~6.html. 2020-07-17.
  23. Web site: The Linked Open Data Cloud. 2020-06-30. lod-cloud.net.
  24. Pyne . Yvette . Stewart . Stuart . March 2022 . Meta-work: how we research is as important as what we research . . 72 . 716 . 130–131 . 35210247 . 8884432 . 10.3399/bjgp22X718757.
  25. Web site: Neo4j Graph Database & Analytics Graph Database Management System . 8 November 2023 . Neo4j.
  26. Web site: Ontotext GraphDB . 8 November 2023 . Ontotext.
  27. Web site: An Enterprise Graph Database Management System . 19 February 2025 . Bitnine.net.
  28. Web site: Sa . Wang . 2025-02-07 . Knowledge Graph . 2025-08-18 . www.puppygraph.com.
  29. Xiao . Guohui . Ding . Linfang . Cogrel . Benjamin . Calvanese . Diego . Virtual Knowledge Graphs: An Overview of Systems and Use Cases . Data Intelligence . 2019 . 1 . 3 . 201–223 . 10.1162/dint_a_00011 . free .
  30. Web site: 2022-04-05. How do knowledge graphs work?. 2022-04-05. Stardog. en-US.
  31. Web site: 2023-09-01 . Unlocking the Power of Google Knowledge Panel: How to Obtain and Claim Yours in 2023 – RH Razu . 2023-09-05 . rhrazu.com . en-US.
  32. Web site: Jens . Lehmann . 2021-07-15 . Representation Learning in Knowledge Graphs . 2025-08-18 . jens-lehmann.org.
  33. Book: Hongwei Wang. Proceedings of the 27th ACM International Conference on Information and Knowledge Management . RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems . October 2018. 417–426. 10.1145/3269206.3271739. 1803.03467. 9781450360142 . 3766110.
  34. Zhou . Jie . Cui . Ganqu . 1 . 2020 . Graph neural networks: A review of methods and applications. . AI Open . 1 . 1 . 57–81 . 10.1016/j.aiopen.2021.01.001 . 56517517 . Elsevier Science Direct. free . 1812.08434 .
  35. Ye . Zi . Kumar . Yogan Jaya . Sing . Goh Ong . Song . Fengyan . Wang . Junsong . 2022 . A comprehensive survey of graph neural networks for knowledge graphs. . IEEE Access . 10 . 75729–7574 . 10.1109/ACCESS.2022.3191784 . 2022IEEEA..1075729Y . 250654689 . IEEE Xplore. free .
  36. Berrendorf . Max . Faerman . Evgeniy . Melnychuk . Valentyn . Tresp . Volker . Seidl . Thomas . April 14–17, 2020 . Knowledge graph entity alignment with graph convolutional networks: lessons learned . Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal . Lecture Notes in Computer Science . Proceedings, Part II . 3–11 . 10.1007/978-3-030-45442-5_1 . 1911.08342 . 978-3-030-45441-8 . 208158314 . Springer International Publishing.
  37. Zequn . Sun . Qingheng . Zhang . Wei . Hu . Chengming . Wang . Muhao . Chen . Farahnaz . Akrami . Chengkai . Li . 2020-03-26 . A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs . 2025-08-18 . Proceedings of the VLDB Endowment . 13 . 12 . 2326–2340 . 10.14778/3407790.3407828 . 2003.07743 .
  38. Chaurasiya . Deepak . Surisetty . Anil . Kumar . Nitish . Singh . Alok . Dey . Vikrant . Malhotra . Aakarsh . Dhama . Gaurav . Arora . Ankur . 2022 . Entity alignment for knowledge graphs: progress, challenges, and empirical studies . cs.AI . 2205.08777 .
  39. Hogan . Aidan . Lippolis . Anna Sofia . Klironomos . Antonis . Milon-Flores . Daniela F. . Zheng . Heng . Jouglar . Alexane . Norouzi . Ebrahim . 2023 . Enhancing Entity Alignment Between Wikidata and ArtGraph using LLMs . Proceedings of the International Workshop on Semantic Web and Ontology Design for Cultural Heritage . International Workshop on Semantic Web and Ontology Design for Cultural Heritage (SWODCH), Athens, Greece.

This article is licensed under the GNU Free Documentation License. It uses material from the Wikipedia article "Knowledge graph".

Except where otherwise indicated, Everything.Explained.Today is © Copyright 2009-2026, A B Cryer, All Rights Reserved. Cookie policy.