.png){kind=icon}
Return
Multigraph Fusion for Dynamic Graph Convolutional Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3172588.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph convolutional network (GCN) outputs powerful representation by considering the structure information of the data to conduct representation learning, but its robustness is sensitive to the quality of both the feature matrix and the initial graph. In this article, we propose a novel multigraph fusion method to produce a high-quality graph and a low-dimensional space of original high-dimensional data for the GCN model. Specifically, the proposed method first extracts the common information and the complementary information among multiple local graphs to obtain a unified local graph, which is then fused with the global graph of the data to obtain the initial graph for the GCN model. As a result, the proposed method conducts the graph fusion process twice to simultaneously learn the low-dimensional space and the intrinsic graph structure of the data in a unified framework. Experimental results on real datasets demonstrated that our method outperformed the comparison methods in terms of classification tasks.
Keywords:
Representation learning
Data models
Termination of employment
Learning systems
Task analysis
Robustness
Computer science
Data fusion
dimensionality reduction
graph convolutional networks (GCNs)
graph learning
Journal
IF:
8.9
Papers:
7.6K
Citations:
7.2W
Organization
Cited Papers
ShareSaveInterpretable learning based Dynamic Graph Convolutional Networks for Alzheimer's Disease analysis.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
ShareSave
ShareSave
View more