Learning Deep Graph Representations via Convolutional Neural Networks

被引:8
作者
Ye, Wei [1 ]
Askarisichani, Omid [1 ]
Jones, Alex [1 ]
Singh, Ambuj [1 ]
机构
[1] Univ Calif Santa Barbara, Dept Comp Sci, Santa Barbara, CA 93106 USA
基金
美国国家科学基金会;
关键词
Kernel; Feature extraction; Convolutional neural networks; Benchmark testing; Natural languages; Shape; Deep learning; representation learning; convolutional neural networks; feature maps; graph kernels; graphlet; shortest path; Weisfeiler-Lehman; PREDICTION; KERNELS;
D O I
10.1109/TKDE.2020.3014089
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph-structured data arise in many scenarios. A fundamental problem is to quantify the similarities of graphs for tasks such as classification. R-convolution graph kernels are positive-semidefinite functions that decompose graphs into substructures and compare them. One problem in the effective implementation of this idea is that the substructures are not independent, which leads to high-dimensional feature space. In addition, graph kernels cannot capture the high-order complex interactions between vertices. To mitigate these two problems, we propose a framework called DeepMap to learn deep representations for graph feature maps. The learned deep representation for a graph is a dense and low-dimensional vector that captures complex high-order interactions in a vertex neighborhood. DeepMap extends Convolutional Neural Networks (CNNs) to arbitrary graphs by generating aligned vertex sequences and building the receptive field for each vertex. We empirically validate DeepMap on various graph classification benchmarks and demonstrate that it achieves state-of-the-art performance.
引用
收藏
页码:2268 / 2279
页数:12
相关论文
共 48 条
[1]  
[Anonymous], 1994, Graph theory
[2]  
Arora S, 2019, 33 C NEURAL INFORM P, V32
[3]  
Atwood J., 2016, P NIPS, P1993
[4]   A quantum Jensen-Shannon graph kernel for unattributed graphs [J].
Bai, Lu ;
Rossi, Luca ;
Torsello, Andrea ;
Hancock, Edwin R. .
PATTERN RECOGNITION, 2015, 48 (02) :344-355
[5]  
BONACICH P, 1987, AM J SOCIOL, V92, P1170, DOI 10.1086/228631
[6]   Shortest-path kernels on graphs [J].
Borgwardt, KM ;
Kriegel, HP .
Fifth IEEE International Conference on Data Mining, Proceedings, 2005, :74-81
[7]   Protein function prediction via graph kernels [J].
Borgwardt, KM ;
Ong, CS ;
Schönauer, S ;
Vishwanathan, SVN ;
Smola, AJ ;
Kriegel, HP .
BIOINFORMATICS, 2005, 21 :I47-I56
[8]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[9]   DeepTrend 2.0: A light-weighted multi-scale traffic prediction model using detrending [J].
Dai, Xingyuan ;
Fu, Rui ;
Zhao, Enmin ;
Zhang, Zuo ;
Lin, Yilun ;
Wang, Fei-Yue ;
Li, Li .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2019, 103 :142-157
[10]  
Defferrard M, 2016, ADV NEUR IN, V29