Entity alignment via graph neural networks: a component-level study
Article
Shu, Yanfeng, Zhang, Ji, Huang, Guangyan, Chi, Chi-Hung and He, Jing. 2023. "Entity alignment via graph neural networks: a component-level study." World Wide Web. 26 (6), pp. 4069-4092. https://doi.org/10.1007/s11280-023-01221-8
Article Title | Entity alignment via graph neural networks: a component-level study |
---|---|
ERA Journal ID | 32110 |
Article Category | Article |
Authors | Shu, Yanfeng, Zhang, Ji, Huang, Guangyan, Chi, Chi-Hung and He, Jing |
Journal Title | World Wide Web |
Journal Citation | 26 (6), pp. 4069-4092 |
Number of Pages | 24 |
Year | 2023 |
Publisher | Springer |
Place of Publication | United States |
ISSN | 1386-145X |
1573-1413 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/s11280-023-01221-8 |
Web Address (URL) | https://link.springer.com/article/10.1007/s11280-023-01221-8 |
Abstract | Entity alignment plays an essential role in the integration of knowledge graphs (KGs) as it seeks to identify entities that refer to the same real-world objects across different KGs. Recent research has primarily centred on embedding-based approaches. Among these approaches, there is a growing interest in graph neural networks (GNNs) due to their ability to capture complex relationships and incorporate node attributes within KGs. Despite the presence of several surveys in this area, they often lack comprehensive investigations specifically targeting GNN-based approaches. Moreover, they tend to evaluate overall performance without analysing the impact of individual components and methods. To bridge these gaps, this paper presents a framework for GNN-based entity alignment that captures the key characteristics of these approaches. We conduct a fine-grained analysis of individual components and assess their influences on alignment results. Our findings highlight specific module options that significantly affect the alignment outcomes. By carefully selecting suitable methods for combination, even basic GNN networks can achieve competitive alignment results. |
Keywords | Entity alignment; Knowledge graph; Graph neural networ |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 461299. Software engineering not elsewhere classified |
Byline Affiliations | Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia |
University of Southern Queensland | |
Deakin University | |
Nanyang Technological University, Singapore | |
University of Oxford, United Kingdom |
Permalink -
https://research.usq.edu.au/item/zq35x/entity-alignment-via-graph-neural-networks-a-component-level-study
Download files
14
total views2
total downloads14
views this month2
downloads this month