Bilinear Graph Neural Network with Neighbor Interactions

Abstract

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.

arXiv commentAccepted by IJCAI 2020. SOLE copyright holder is IJCAI (International Joint Conferences on Artificial Intelligence), all rights reserved

References in corpus (13)

• DeepWalk: Online Learning of Social Representations
• Inductive Representation Learning on Large Graphs
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• Diffusion-Convolutional Neural Networks
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Hyperbolic Graph Convolutional Neural Networks
• Neural Factorization Machines for Sparse Predictive Analytics
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Deep Learning on Graphs: A Survey
• Graph Wavelet Neural Network