.png){kind=icon}
返回
Multiscale Representation Learning of Graph Data With Node Affinity
.png){kind=icon}
PRE
AI
DOI：10.1109/TSIPN.2020.3044913.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
Convolution
Topology
Kernel
Network topology
Laplace equations
Information processing
Task analysis
Graph classification
graph neural networks
graph pooling
node affinity
spectral graph theory
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.9
论文数:
739
被引数:
1.9K
机构
引用论文
分享收藏ACE: Ant Colony Based Multi-Level Network Embedding for Hierarchical Graph Representation Learning.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Tinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients耳鸣再训练疗法 (TRT) 作为治疗耳鸣和高亢患者的方法
PREAI
分享收藏Mechanical characterization of neural electrodes based on PDMS-parylene C-PDMS sandwiched system
PREAI
分享收藏Graph Signal Processing: Overview, Challenges, and Applications图信号处理: 概述、挑战与应用PROCEEDINGS OF THE IEEEOAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏分享收藏
查看更多内容