Article: A survey on knowledge graph evolution: proliferation, dynamic embedding, and versioning Journal: International Journal of Web and Grid Services (IJWGS) 2025 Vol.21 No.1 pp.88 - 111 Abstract: In the era of large language models (LLMs), knowledge graphs (KGs) can play a pivotal role in enhancing LLMs by providing a structured representation of knowledge, relationships, and entities. This knowledge is essential for LLMs to understand and interpret information in a coherent and contextually relevant manner. KGs must undergo continuous evolution with minimal human intervention to remain effective. Organisations often employ automated techniques, such as web scraping, natural language processing, and machine learning algorithms, to accomplish this continuous evolution. However, there is a lack of reviews covering recent advances in KG evolution. In this survey, we first give an overview and then describe the methods of KG evolution. Afterward, we review and analyse the evaluation metrics, datasets, and experimental performances. Finally, we provide findings and future directions from the investigation and conclude with a discussion. Inderscience Publishers - linking academia, business and industry through research

Title: A survey on knowledge graph evolution: proliferation, dynamic embedding, and versioning

Authors: Xiongnan Jin; Zhilin Wang; Manni Duan; Yan Shao; Xingyun Hong; Yongheng Wang; Byungkook Oh

Addresses: National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China ' Alibaba Group, Hangzhou, China ' Zhejiang Laboratory, Hangzhou, China ' China Mobile (Hangzhou) Information Technology Co., Ltd., Hangzhou, China ' Zhejiang Laboratory, Hangzhou, China ' Zhejiang Laboratory, Hangzhou, China ' Computer Science and Engineering, Konkuk University, Seoul, South Korea

Abstract: In the era of large language models (LLMs), knowledge graphs (KGs) can play a pivotal role in enhancing LLMs by providing a structured representation of knowledge, relationships, and entities. This knowledge is essential for LLMs to understand and interpret information in a coherent and contextually relevant manner. KGs must undergo continuous evolution with minimal human intervention to remain effective. Organisations often employ automated techniques, such as web scraping, natural language processing, and machine learning algorithms, to accomplish this continuous evolution. However, there is a lack of reviews covering recent advances in KG evolution. In this survey, we first give an overview and then describe the methods of KG evolution. Afterward, we review and analyse the evaluation metrics, datasets, and experimental performances. Finally, we provide findings and future directions from the investigation and conclude with a discussion.

Keywords: knowledge graph evolution; KG proliferation; fact validation; property error detection; PED; rule mining; KG dynamic embedding; KG versioning; large language model; LLM.

DOI: 10.1504/IJWGS.2025.144974

International Journal of Web and Grid Services, 2025 Vol.21 No.1, pp.88 - 111

Received: 29 Dec 2023
Accepted: 27 Sep 2024
Published online: 14 Mar 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A survey on knowledge graph evolution: proliferation, dynamic embedding, and versioning

Keep up-to-date