GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
This work addresses a limitation in graph representation learning for tasks like node classification and link prediction, offering an incremental improvement over existing GCN-based models.
The paper tackles the problem that graph convolutional networks (GCNs) struggle to capture complex non-linearity in graph data, and proposes GraphAIR, a framework that models neighborhood interaction alongside aggregation, showing effectiveness in node classification and link prediction tasks on public datasets.
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.