GraphAIR: Graph representation learning with neighborhood aggregation and interaction

•We prove that existing GCN-based models have difficulty in well capturing complicated non-linearity of graph data. Compared with other GNN variants, our work explicitly models neighborhood interaction for better capturing non-linearity of node features.•The proposed architecture can easily integrate off-the-shelf graph convolutional models, which shows favorable generality. Our proposed approach is as asymptotically efficient as the underlying graph convolutional model.•Our proposed method based on well-known models including GCN, GraphSAGE, and GAT have been thoroughly investigated through empirical evaluation. Extensive experiments conducted on benchmark tasks of node classification and link prediction illustrate the effectiveness of our proposed method. Graph representation learning is of paramount importance for a variety of graph analytical tasks, ranging from node classification to community detection. Recently, graph convolutional networks (GCNs) have been successfully applied for graph representation learning. These GCNs generate node representation by aggregating features from the neighborhoods, which follows the “neighborhood aggregation” scheme. In spite of having achieved promising performance on various tasks, existing GCN-based models have difficulty in well capturing complicated non-linearity of graph data. In this paper, we first theoretically prove that coefficients of the neighborhood interacting terms are relatively small in current models, which explains why GCNs barely outperforms linear models. Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation. Comprehensive experiments conducted on benchmark tasks including node classification and link prediction using public datasets demonstrate the effectiveness of the proposed method.