Graph Convolutional Networks with EigenPooling

Abstract

Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks such as node classification and link prediction. To apply graph neural networks for the graph classification task, approaches to generate the \textit{graph representation} from node representations are demanded. A common way is to globally combine the node representations. However, rich structural information is overlooked. Thus a hierarchical pooling procedure is desired to preserve the graph structure during the graph representation learning. There are some recent works on hierarchically learning graph representation analogous to the pooling step in conventional convolutional neural (CNN) networks. However, the local structural information is still largely neglected during the pooling process. In this paper, we introduce a pooling operator $\pooling$ based on graph Fourier transform, which can utilize the node features and local structures during the pooling process. We then design pooling layers based on the pooling operator, which are further combined with traditional GCN convolutional layers to form a graph neural network framework $\m$ for graph classification. Theoretical analysis is provided to understand $\pooling$ from both local and global perspectives. Experimental results of the graph classification task on $6$ commonly used benchmarks demonstrate the effectiveness of the proposed framework.

References in corpus (17)

• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Deep Convolutional Networks on Graph-Structured Data
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Gated Graph Sequence Neural Networks
• Perfect Reconstruction Two-Channel Wavelet Filter-Banks for Graph Structured Data
• Graph networks as learnable physics engines for inference and control
• Order Matters: Sequence to sequence for sets
• Deep Learning on Graphs: A Survey
• Subgraph-based filterbanks for graph signals
• Graph Neural Networks for Social Recommendation
• Signed Graph Convolutional Network
• Streaming Graph Neural Networks

Cited by in corpus (5)

• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Understanding Pooling in Graph Neural Networks
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
• Learning Hierarchical Review Graph Representations for Recommendation