Second-Order Pooling for Graph Neural Networks

Abstract

Graph neural networks have achieved great success in learning node representations for graph tasks such as node classification and link prediction. Graph representation learning requires graph pooling to obtain graph representations from node representations. It is challenging to develop graph pooling methods due to the variable sizes and isomorphic structures of graphs. In this work, we propose to use second-order pooling as graph pooling, which naturally solves the above challenges. In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order statistics, making it more powerful. We show that direct use of second-order pooling with graph neural networks leads to practical problems. To overcome these problems, we propose two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second-order pooling. In addition, we extend attentional second-order pooling to hierarchical graph pooling for more flexible use in GNNs. We perform thorough experiments on graph classification tasks to demonstrate the effectiveness and superiority of our proposed methods. Experimental results show that our methods improve the performance significantly and consistently.

12 pages, 2 figures, https://www.computer.org/csdl/journal/tp/5555/01/09104936/1kj0O2A1yBa

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A Comprehensive Survey on Graph Neural Networks
• Inductive Representation Learning on Large Graphs
• Representation Learning on Graphs with Jumping Knowledge Networks
• Hierarchical Graph Representation Learning with Differentiable Pooling
• Diffusion-Convolutional Neural Networks
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Self-Attention Graph Pooling
• Attentional Pooling for Action Recognition
• Anonymous Walk Embeddings
• Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
• Graph Capsule Convolutional Neural Networks
• Learning Convolutional Text Representations for Visual Question Answering

Cited by in corpus (11)

• BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck
• Real-time Hosting Capacity Assessment for Electric Vehicles: A Sequential Forecast-then-Optimize Method
• Revisiting 2D Convolutional Neural Networks for Graph-based Applications
• Topology-Aware Graph Pooling Networks
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks
• Learnable Structural Semantic Readout for Graph Classification
• Embedding Graphs on Grassmann Manifold
• Tree-Constrained Graph Neural Networks For Argument Mining
• Structural Optimization Makes Graph Classification Simpler and Better
• Graph Size-imbalanced Learning with Energy-guided Structural Smoothing
• MSHCNet: Multi-Stream Hybridized Convolutional Networks with Mixed Statistics in Euclidean/Non-Euclidean Spaces and Its Application to Hyperspectral Image Classification