2020
DOI: 10.3390/electronics9030432
|View full text |Cite
|
Sign up to set email alerts
|

Structure Fusion Based on Graph Convolutional Networks for Node Classification in Citation Networks

Abstract: Suffering from the multi-view data diversity and complexity, most of the existing graph convolutional networks focus on the networks’ architecture construction or the salient graph structure preservation for node classification in citation networks and usually ignore capturing the complete graph structure of nodes for enhancing classification performance. To mine the more complete distribution structure from multi-graph structures of multi-view data with the consideration of their specificity and the commonali… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(2 citation statements)
references
References 25 publications
(45 reference statements)
0
2
0
Order By: Relevance
“…Thus, the spatial structure features of the topological graph are extracted from the graph. Common neural network methods include GCN 21 , GraphSAGE 22 , GAT 23 , etc. Community detection is to use a Euclidean space clustering method, such as k-means 24 , on the data obtained after graph embedding to identify the clusters of the graph 25 , 26 .…”
Section: Related Workmentioning
confidence: 99%
“…Thus, the spatial structure features of the topological graph are extracted from the graph. Common neural network methods include GCN 21 , GraphSAGE 22 , GAT 23 , etc. Community detection is to use a Euclidean space clustering method, such as k-means 24 , on the data obtained after graph embedding to identify the clusters of the graph 25 , 26 .…”
Section: Related Workmentioning
confidence: 99%
“…According to Grassmann theory, each orthonormal matrix forms a unique subspace, so it can be mapped to a unique point in the Grassmann manifold (Lin et al, 2020). Since the eigenvector matrix of the normalized Laplacian matrix (U ∈ R n×p ), which contains the first p eigenvectors, is orthonormal (Wu et al, 2020), it also forms a unique subspace that can map a single point on the Grassmann manifold.…”
Section: Mergingmentioning
confidence: 99%