TY - GEN
T1 - Multi-dimensional graph convolutional networks
AU - Ma, Yao
AU - Wang, Suhang
AU - Aggarwal, Charu C.
AU - Yin, Dawei
AU - Tang, Jiliang
N1 - Publisher Copyright:
Copyright © 2019 by SIAM.
PY - 2019
Y1 - 2019
N2 - Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video. Recently, increasing attention has been paid on generalizing CNNs to graph or network data which is highly irregular. Some focus on graph-level representation learning while others aim to learn node-level representations. These methods have been shown to boost the performance of many graph-level tasks such as graph classification and node-level tasks such as node classification. Most of these methods have been designed for single-dimensional graphs where a pair of nodes can only be connected by one type of relation. However, many real-world graphs have multiple types of relations and they can be naturally modeled as multi-dimensional graphs with each type of relation as a dimension. Multi-dimensional graphs bring about richer interactions between dimensions, which poses tremendous challenges to the graph convolutional neural networks designed for single-dimensional graphs. In this paper, we study the problem of graph convolutional networks for multidimensional graphs and propose a multi-dimensional convolutional neural network model mGCN aiming to capture rich information in learning node-level representations for multi-dimensional graphs. Comprehensive experiments on real-world multi-dimensional graphs demonstrate the effectiveness of the proposed framework.
AB - Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video. Recently, increasing attention has been paid on generalizing CNNs to graph or network data which is highly irregular. Some focus on graph-level representation learning while others aim to learn node-level representations. These methods have been shown to boost the performance of many graph-level tasks such as graph classification and node-level tasks such as node classification. Most of these methods have been designed for single-dimensional graphs where a pair of nodes can only be connected by one type of relation. However, many real-world graphs have multiple types of relations and they can be naturally modeled as multi-dimensional graphs with each type of relation as a dimension. Multi-dimensional graphs bring about richer interactions between dimensions, which poses tremendous challenges to the graph convolutional neural networks designed for single-dimensional graphs. In this paper, we study the problem of graph convolutional networks for multidimensional graphs and propose a multi-dimensional convolutional neural network model mGCN aiming to capture rich information in learning node-level representations for multi-dimensional graphs. Comprehensive experiments on real-world multi-dimensional graphs demonstrate the effectiveness of the proposed framework.
UR - http://www.scopus.com/inward/record.url?scp=85066089424&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066089424&partnerID=8YFLogxK
U2 - 10.1137/1.9781611975673.74
DO - 10.1137/1.9781611975673.74
M3 - Conference contribution
AN - SCOPUS:85066089424
T3 - SIAM International Conference on Data Mining, SDM 2019
SP - 657
EP - 665
BT - SIAM International Conference on Data Mining, SDM 2019
PB - Society for Industrial and Applied Mathematics Publications
T2 - 19th SIAM International Conference on Data Mining, SDM 2019
Y2 - 2 May 2019 through 4 May 2019
ER -