Bilinear Graph Neural Network with Neighbor Interactions
This work addresses a limitation in GNNs for graph data analysis, offering a modest improvement in accuracy for node classification tasks.
The paper tackles the problem that existing Graph Neural Networks (GNNs) ignore interactions between neighbor nodes, which can be crucial signals for node characteristics, by proposing a Bilinear Graph Neural Network (BGNN) that augments weighted sum with pairwise interactions. The result shows BGCN and BGAT outperform GCN and GAT by 1.6% and 1.5% in classification accuracy on semi-supervised node classification benchmarks.
Graph Neural Network (GNN) is a powerful model to learn representations and make predictions on graph data. Existing efforts on GNN have largely defined the graph convolution as a weighted sum of the features of the connected nodes to form the representation of the target node. Nevertheless, the operation of weighted sum assumes the neighbor nodes are independent of each other, and ignores the possible interactions between them. When such interactions exist, such as the co-occurrence of two neighbor nodes is a strong signal of the target node's characteristics, existing GNN models may fail to capture the signal. In this work, we argue the importance of modeling the interactions between neighbor nodes in GNN. We propose a new graph convolution operator, which augments the weighted sum with pairwise interactions of the representations of neighbor nodes. We term this framework as Bilinear Graph Neural Network (BGNN), which improves GNN representation ability with bilinear interactions between neighbor nodes. In particular, we specify two BGNN models named BGCN and BGAT, based on the well-known GCN and GAT, respectively. Empirical results on three public benchmarks of semi-supervised node classification verify the effectiveness of BGNN -- BGCN (BGAT) outperforms GCN (GAT) by 1.6% (1.5%) in classification accuracy.Codes are available at: https://github.com/zhuhm1996/bgnn.