Large-Scale Learnable Graph Convolutional Networks

Abstract

Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic extraction of high-level features. The computation with filters requires a fixed number of ordered units in the receptive fields. However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations. Here, we address these challenges by proposing the learnable graph convolutional layer (LGCL). LGCL automatically selects a fixed number of neighboring nodes for each feature based on value ranking in order to transform graph data into grid-like structures in 1-D format, thereby enabling the use of regular convolutional operations on generic graphs. To enable model training on large-scale graphs, we propose a sub-graph training method to reduce the excessive memory and computational resource requirements suffered by prior methods on graph convolutions. Our experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that our methods can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network datasets. Our results also indicate that the proposed methods using sub-graph training strategy are more efficient as compared to prior approaches.

References in corpus (2)

• DeepWalk: Online Learning of Social Representations
• Predicting multicellular function through multi-layer tissue networks

Cited by in corpus (29)

• A Comprehensive Survey on Graph Neural Networks
• Towards Deeper Graph Neural Networks
• Graph Learning: A Survey
• Scaling Graph Neural Networks with Approximate PageRank
• Graph Representation Learning: A Survey
• GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals
• Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information
• Graph Neural Networks: Taxonomy, Advances and Trends
• TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
• Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction
• K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
• Accurate, Efficient and Scalable Graph Embedding
• C-SAW: A Framework for Graph Sampling and Random Walk on GPUs
• Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
• Kronecker Attention Networks
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• AutoGraph: Automated Graph Neural Network
• Non-Local Graph Neural Networks
• Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network
• Bayesian graph convolutional neural networks via tempered MCMC
• Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
• GraphPAS: Parallel Architecture Search for Graph Neural Networks
• A Network Science perspective of Graph Convolutional Networks: A survey
• Action Sequence Augmentation for Early Graph-based Anomaly Detection
• Enhancing Road Safety through Accurate Detection of Hazardous Driving Behaviors with Graph Convolutional Recurrent Networks
• Structure fusion based on graph convolutional networks for semi-supervised classification
• Network Embedding via Deep Prediction Model
• GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
• Alleviating Over-Smoothing via Aggregation over Compact Manifolds