GraphAIR: Graph representation learning with neighborhood aggregation and interaction

Highlights：

• 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.

摘要

•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.

论文关键词：Graph representation learning,Neighborhood aggregation,Graph neural networks,Neighborhood interaction,Node classification,Link prediction

论文评审过程：Received 25 February 2020, Revised 5 August 2020, Accepted 31 October 2020, Available online 8 November 2020, Version of Record 30 January 2021.