2022
DOI: 10.1016/j.ipm.2021.102790
|View full text |Cite
|
Sign up to set email alerts
|

Multi-heterogeneous neighborhood-aware for Knowledge Graphs alignment

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
2
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(5 citation statements)
references
References 8 publications
0
2
0
Order By: Relevance
“…N-gram [18] uses the attribute triples to generate the embeddings for attribute characters. Other works [1][21] also merge additional configuration information for entities by entities' attributes. 2) Changing the range of neighborhood.…”
Section: B Methods For Non-isomorphic Cleamentioning
confidence: 99%
See 1 more Smart Citation
“…N-gram [18] uses the attribute triples to generate the embeddings for attribute characters. Other works [1][21] also merge additional configuration information for entities by entities' attributes. 2) Changing the range of neighborhood.…”
Section: B Methods For Non-isomorphic Cleamentioning
confidence: 99%
“…It is worthy to note that a few recent works [1][3] [28] have achieved remarkable performances. [1][28] use some additional information, such as entities' attribute information and entities' description information. [3][28] initialize the representation with Glove embedding.…”
Section: A Datasets and Baselinesmentioning
confidence: 99%
“…In addition to using GCN to extract the entity relations and attribute information, HMAN [31] also utilizes BERT to extract the textual description information about the entities for entity information modeling. MHNA [32] improves the alignment performance by designing a variable attention mechanism based on heterogeneous graphs. To better utilize the entity attribute information, GRGCN [33] employs a combination of graph convolutional neural networks and graph attention networks for entity alignment.…”
Section: Entity Alignmentmentioning
confidence: 99%
“…In [35], a heterogeneous network HeCo is proposed, which generates meta-paths and network schemas and exploits contrastive learning to further use signals of data in a self-supervised manner. Wang et al [31] and Cai et al [3] created item clusters and entity clusters to organise the objects and their nearby entities in the knowledge graph. After that, the hierarchically combining the heterogeneity data derived from the clusters with the weights produced by the hierarchical attention layers yields the representations.…”
Section: Heterogeneous Graph Neural Networkmentioning
confidence: 99%