Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology

被引：39

作者：

Cheung, Mark ^{[1
]}

Shi, John ^{[1
]}

Wright, Oren ^{[2
]}

Jiang, Lavendar Y. ^{[1
,3
]}

Liu, Xujin ^{[1
]}

Moura, Jose M. F. ^{[4
,5
,6
,7
]}

机构：

[1] Carnegie Mellon Univ, Elect & Comp Engn Dept, Pittsburgh, PA 15213 USA

[2] Carnegie Mellon Univ, Inst Software Engn, Pittsburgh, PA 15213 USA

[3] Carnegie Mellon Univ, Dept Math Sci, Pittsburgh, PA 15213 USA

[4] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

[5] Amer Assoc Advancement Sci, Pittsburgh, PA USA

[6] Portugal Acad Sci, Lisbon, Portugal

[7] US Natl Acad Engineers, Washington, DC USA

来源：

IEEE SIGNAL PROCESSING MAGAZINE | 2020年 / 37卷 / 06期

基金：

美国国家科学基金会; 美国安德鲁·梅隆基金会;

关键词：

Convolution; Deep learning; Computer architecture; Graphical models; Filtering theory; Discrete Fourier transforms;

D O I：

10.1109/MSP.2020.3014594

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：139 / 149

页数：11

共 50 条

[1] Star topology convolution for graph representation learning
Chong Wu
Zhenan Feng
Jiangbin Zheng
Houwang Zhang
Jiawang Cao
Hong Yan
Complex & Intelligent Systems, 2022, 8 : 5125 - 5141
[2] Star topology convolution for graph representation learning
Wu, Chong
Feng, Zhenan
Zheng, Jiangbin
Zhang, Houwang
Cao, Jiawang
Yan, Hong
COMPLEX & INTELLIGENT SYSTEMS, 2022, 8 (06) : 5125 - 5141
[3] Topology-Aware Graph Signal Sampling for Pooling in Graph Neural Networks
Nouranizadeh, Amirhossein
Matinkia, Mohammadjavad
Rahmati, Mohammad
2021 26TH INTERNATIONAL COMPUTER CONFERENCE, COMPUTER SOCIETY OF IRAN (CSICC), 2021,
[4] Topics in Graph Signal Processing: Convolution and Modulation
Shi, John
Moura, Jose M. F.
CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, 2019, : 457 - 461
[5] Graph convolution with topology refinement for Automatic Reinforcement Learning
Sang, Jianghui
Wang, Yongli
NEUROCOMPUTING, 2023, 554
[6] Graph Signal Processing in the Presence of Topology Uncertainties
Ceci, Elena
Barbarossa, Sergio
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2020, 68 : 1558 - 1573
[7] Robust Graph Signal Processing in the Presence of Uncertainties on Graph Topology
Ceci, Elena
Barbarossa, Sergio
2018 IEEE 19TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC), 2018, : 656 - 660
[8] On the Computational Power of Convolution Pooling: A Theoretical Approach for Deep Learning
Nakano, Koji
Aoki, Shotaro
Ito, Yasuaki
Kasagi, Akihiko
2021 IEEE INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2021, : 656 - 665
[9] Graph Linear Convolution Pooling for Learning in Incomplete High-Dimensional Data
Bi, Fanghui
He, Tiantian
Ong, Yew-Soon
Luo, Xin
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2025, 37 (04) : 1838 - 1852
[10] A New Framework Containing Convolution and Pooling Circuits for Image Processing and Deep Learning Applications with Quantum Computing Implementation
Yetis, Hasan
Karakose, Mehmet
TRAITEMENT DU SIGNAL, 2022, 39 (02) : 501 - 512

← 1 2 3 4 5 →