Motif-based Convolutional Neural Network on Graphs
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.
References in corpus (9)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Inductive Representation Learning on Large Graphs
- Higher-order organization of complex networks
- Biological network comparison using graphlet degree distribution
- Learning Convolutional Neural Networks for Graphs
- Robust Spatial Filtering with Graph Convolutional Neural Networks
- Detecting Strong Ties Using Network Motifs
- Stochastic Graphlet Embedding
- Improving Latent User Models in Online Social Media
Cited by in corpus (4)
- Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction
- HONEM: Learning Embedding for Higher Order Networks
- Graph Convolutional Neural Networks via Motif-based Attention
- User-Guided Clustering in Heterogeneous Information Networks via Motif-Based Comprehensive Transcription