Graph Convolutional Neural Networks via Motif-based Attention
This work addresses graph classification problems in domains like bioinformatics and social networks, representing an incremental advance with a novel method for a known bottleneck.
The paper tackles graph classification by proposing a novel framework that uses motif-based attention and subgraph normalization to capture neighborhood information, achieving significant improvements over traditional graph kernel and existing deep models on bioinformatics and social network datasets.
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.