Motif-based Convolutional Neural Network on Graphs

2017/11/15 by Sankar, Aravind, Zhang, Xinyang, Chang, Kevin Chen-Chuan
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Social and Information Networks (cs.SI)

paper · doi:10.48550/arxiv.1711.05697

Abstract

This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using high-order connection patterns or motifs. We develop a novel deep architecture Motif-CNN that employs an attention model to combine the features extracted from multiple patterns, thus effectively capturing high-order structural and feature information. Our experiments on semi-supervised node classification on real-world social networks and multiple representative heterogeneous graph datasets indicate significant gains of 6-21% over existing graph CNNs and other state-of-the-art techniques.

Related

• Graph Convolutional Neural Networks via Motif-based Attention
• Higher-order Graph Convolutional Networks
• motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks
• MotifNet: a motif-based Graph Convolutional Network for directed graphs
• Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs