AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism

Graph convolutional networks (GCNs) are potentially insufficient in the ability to learn hierarchical representation for graph embedding, which holds them back in the graph classification task. To address the insufficiency, we propose AttPool, which is a novel graph pooling module based on an attention based mechanism, to remedy the problem. It is able to select nodes that are significant for graph representation adaptively, and generate hierarchical features via aggregating the attention-weighted information in nodes. Additionally, we devise a hierarchical prediction architecture to sufficiently leverage the hierarchical representation and facilitate the model learning. The AttPool module together with the entire training structure can be integrated into existing GCNs, and is trained in an end-toend fashion conveniently. The experimental results on several graph-classification benchmark datasets with various scales demonstrate the effectiveness of our method.