Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

Abstract

We focus on graph classification using a graph neural network (GNN) model that precomputes the node features using a bank of neighborhood aggregation graph operators arranged in parallel. These GNN models have a natural advantage of reduced training and inference time due to the precomputations but are also fundamentally different from popular GNN variants that update node features through a sequential neighborhood aggregation procedure during training. We provide theoretical conditions under which a generic GNN model with parallel neighborhood aggregations (PA-GNNs, in short) are provably as powerful as the well-known Weisfeiler-Lehman (WL) graph isomorphism test in discriminating non-isomorphic graphs. Although PA-GNN models do not have an apparent relationship with the WL test, we show that the graph embeddings obtained from these two methods are injectively related. We then propose a specialized PA-GNN model, called SPIN, which obeys the developed conditions. We demonstrate via numerical experiments that the developed model achieves state-of-the-art performance on many diverse real-world datasets while maintaining the discriminative power of the WL test and the computational advantage of preprocessing graphs before the training process.

References in corpus (15)

• A Comprehensive Survey on Graph Neural Networks
• Inductive Representation Learning on Large Graphs
• Geometric deep learning: going beyond Euclidean data
• Modeling polypharmacy side effects with graph convolutional networks
• Learning Combinatorial Optimization Algorithms over Graphs
• Representation Learning on Graphs with Jumping Knowledge Networks
• MolGAN: An implicit generative model for small molecular graphs
• Learning to Simulate Complex Physics with Graph Networks
• Graph signal processing for machine learning: A review and new perspectives
• SIGN: Scalable Inception Graph Neural Networks
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks
• A Fair Comparison of Graph Neural Networks for Graph Classification
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis
• An Overview on the Application of Graph Neural Networks in Wireless Networks