.png){kind=icon}
返回
WGDPool: A broad scope extraction for weighted graph data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2024.123678.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph pooling is a commonly used operation in graph neural networks to reduce the size of graph representation. To extract key information, pooling and representation need to be coupled. We propose a graph pooling method for weighted graphs called WGDPool (Weighted Graph Dual Pooling). Unlike traditional graph representation learning methods, the weight information of edges is also fed into convolutional graph neural networks (ConvGNN) to obtain graph representations. Dual branch convolutional graph neural networks is designed to learn the nodes' and edges' embeddings independently, and they are fused into a comprehensive representation of graph data. Pooling, as a tool of feature extraction and scale reduction of graph representation, adopts a differentiable version of k -means clustering and a multi -item parameterized loss function. Cut loss, orthogonality loss, clustering loss, and reconstruction loss are simultaneously considered. By parameterization, WGDPool is competent for diverse graph tasks. WGDPool outperformed other graph pooling methods in such common supervised and unsupervised tasks as biological or chemical classification, bibliography clustering and integrated circuit partition, demonstrating the effectiveness of our proposed pooling method.
Keyword:
Graph pooling
Graph representation
Graph feature extraction
GNN
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
.png){kind=icon}
Crustal contamination processes traced by helium isotopes: Examples from the Sunda arc, Indonesia
PREAI
分享收藏
查看更多内容