.png){kind=icon}
.png){kind=icon}
Return
Multiscale Representation Learning of Graph Data With Node Affinity
.png){kind=icon}
PRE
AI
DOI：10.1109/TSIPN.2020.3044913.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph neural networks have emerged as a popular and powerful tool for learning hierarchical representation of graph data. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of data in graph neural networks. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node affinity to improve the hierarchical representation learning of graph data. Node affinity is computed by harmonizing the kernel representation of topology information and node features. In particular, a structure-aware kernel representation is introduced to explicitly exploit advanced topological information for efficient graph pooling without eigendecomposition of the graph Laplacian. Similarities of node signals are evaluated using the Gaussian radial basis function (RBF) in an adaptive way. Experimental results demonstrate that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
Keywords:
Convolution
Topology
Kernel
Network topology
Laplace equations
Information processing
Task analysis
Graph classification
graph neural networks
graph pooling
node affinity
spectral graph theory
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.9
Papers:
726
Citations:
1.9K