.png){kind=icon}
Return
A novel graph oversampling framework for node classification in class-imbalanced graphs
.png){kind=icon}
PRE
AI
DOI：10.1007/s11432-023-3897-2.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph neural network (GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in class-imbalanced graphs (named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.
Keywords:
graph neural network
class-imbalanced graphs
sum-product network
oversampling
node classification
Journal
IF:
7.6
Papers:
4.9K
Citations:
8.9K
Organization
Cited Papers
A systematic study of the class imbalance problem in convolutional neural networks.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAIShareSaveShareSaveShareSaveA statistical study of the potential dependence of a transfer coefficient supports the Marcus theory
PREAI
ShareSave
View more