Graph Convolutional Neural Networks via Motif-based Attention
arXiv:1811.08270
Abstract
Many real-world problems can be represented as graph-based learning problems. In this paper, we propose a novel framework for learning spatial and attentional convolution neural networks on arbitrary graphs. Different from previous convolutional neural networks on graphs, we first design a motif-matching guided subgraph normalization method to capture neighborhood information. Then we implement subgraph-level self-attentional layers to learn different importances from different subgraphs to solve graph classification problems. Analogous to image-based attentional convolution networks that operate on locally connected and weighted regions of the input, we also extend graph normalization from one-dimensional node sequence to two-dimensional node grid by leveraging motif-matching, and design self-attentional layers without requiring any kinds of cost depending on prior knowledge of the graph structure. Our results on both bioinformatics and social network datasets show that we can significantly improve graph classification benchmarks over traditional graph kernel and existing deep models.
References in corpus (12)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Graph Neural Networks: A Review of Methods and Applications
- Higher-order organization of complex networks
- Biological network comparison using graphlet degree distribution
- Hierarchical Graph Representation Learning with Differentiable Pooling
- Anonymous Walk Embeddings
- Higher-order clustering in networks
- The Multiscale Laplacian Graph Kernel
- Graph Capsule Convolutional Neural Networks
- Covariant Compositional Networks For Learning Graphs
- Motif-based Convolutional Neural Network on Graphs
- Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks