| Title: | Knowledge graph alignment network with node-level strong fusion |
|---|
| Authors: | ID Liu, Shuang (Author)
ID Xu, Man (Author)
ID Qin, Yufeng (Author)
ID Lukač, Niko (Author) |
|---|
| Files: |  applsci-12-09434-v2.pdf (3,40 MB)
MD5: 926A1DE61E8E1C4ECECB5DBB200132C2
 https://www.mdpi.com/2076-3417/12/19/9434
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | Entity alignment refers to the process of discovering entities representing the same object
in different knowledge graphs (KG). Recently, some studies have learned other information about
entities, but they are aspect-level simple information associations, and thus only rough entity representations can be obtained, and the advantage of multi-faceted information is lost. In this paper, a
novel node-level information strong fusion framework (SFEA) is proposed, based on four aspects:
structure, attribute, relation and names. The attribute information and name information are learned
first, then structure information is learned based on these two aspects of information through graph
convolutional network (GCN), the alignment signals from attribute and name are already carried
at the beginning of the learning structure. In the process of continuous propagation of multi-hop
neighborhoods, the effect of strong fusion of structure, attribute and name information is achieved
and the more meticulous entity representations are obtained. Additionally, through the continuous
interaction between sub-alignment tasks, the effect of entity alignment is enhanced. An iterative
framework is designed to improve performance while reducing the impact on pre-aligned seed pairs.
Furthermore, extensive experiments demonstrate that the model improves the accuracy of entity
alignment and significantly outperforms 13 previous state-of-the-art methods. |
|---|
| Keywords: | knowledge graph, entity ealignment, graph convolutional network, knowledge fusion |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 04.08.2022 |
|---|
| Article acceptance date: | 18.09.2022 |
|---|
| Publication date: | 20.09.2022 |
|---|
| Publisher: | MDPI AG |
|---|
| Year of publishing: | 2022 |
|---|
| Number of pages: | 16 str. |
|---|
| Numbering: | Vol. 12, iss. 19 |
|---|
| PID: | 20.500.12556/DKUM-92293  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 2076-3417 |
|---|
| COBISS.SI-ID: | 126251779 |
|---|
| DOI: | 10.3390/app12199434 |
|---|
| Copyright: | © 2022 by the authors |
|---|
| Publication date in DKUM: | 27.03.2025 |
|---|
| Views: | 140 |
|---|
| Downloads: | 12 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
