GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction

TL;DR

GraphAIR introduces a novel framework that enhances graph neural networks by modeling neighborhood interactions, addressing the limitations of existing GCNs in capturing complex non-linear graph data for improved performance.

Contribution

The paper proposes a new graph representation learning framework, GraphAIR, which incorporates neighborhood interaction modeling to better capture non-linearity in graph data.

Findings

GraphAIR outperforms existing GCN models on benchmark tasks.

Theoretical analysis shows current models have small interaction coefficients.

Experimental results demonstrate improved node classification and link prediction accuracy.

Abstract

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.