.png){kind=icon}
返回
Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology
.png){kind=icon}
OA
AI
DOI：10.1109/MSP.2020.3014594.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning, particularly convolutional neural networks (CNNs), has yielded rapid, significant improvements in computer vision and related domains. But conventional deep learning architectures perform poorly when data have an underlying graph structure, as in social, biological, and many other domains. This article explores 1) how graph signal processing (GSP) can be used to extend CNN components to graphs to improve model performance and 2) how to design the graph CNN architecture based on the topology or structure of the data graph.
Keyword:
Convolution
Deep learning
Computer architecture
Graphical models
Filtering theory
Discrete Fourier transforms
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Graph Signal Processing: Overview, Challenges, and Applications图信号处理: 概述、挑战与应用.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏分享收藏
查看更多内容