GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction

Abstract

Graph representation learning is of paramount importance for a variety of graph analytical tasks, ranging from node classification to community detection. Recently, graph convolutional networks (GCNs) have been successfully applied for graph representation learning. These GCNs generate node representation by aggregating features from the neighborhoods, which follows the "neighborhood aggregation" scheme. In spite of having achieved promising performance on various tasks, existing GCN-based models have difficulty in well capturing complicated non-linearity of graph data. In this paper, we first theoretically prove that coefficients of the neighborhood interacting terms are relatively small in current models, which explains why GCNs barely outperforms linear models. Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation. Comprehensive experiments conducted on benchmark tasks including node classification and link prediction using public datasets demonstrate the effectiveness of the proposed method.

arXiv comment12 pages, accepted to Pattern Recognition

References in corpus (17)

• DeepWalk: Online Learning of Social Representations
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Simplifying Graph Convolutional Networks
• Graph Contrastive Learning with Adaptive Augmentation
• Representation Learning on Graphs with Jumping Knowledge Networks
• Variational Graph Auto-Encoders
• Visualizing the Loss Landscape of Neural Nets
• Towards Deeper Graph Neural Networks
• Deep Graph Contrastive Representation Learning
• Self-Attention Graph Pooling
• GMNN: Graph Markov Neural Networks
• Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation
• Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
• Entropic Dynamic Time Warping Kernels for Co-evolving Financial Time Series Analysis
• Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification

Cited by in corpus (7)

• A Comprehensive Survey on Deep Graph Representation Learning
• Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
• Neural graph embeddings as explicit low-rank matrix factorization for link prediction
• M2GNN: Metapath and Multi-interest Aggregated Graph Neural Network for Tag-based Cross-domain Recommendation
• DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
• Heterogeneous Graph Collaborative Filtering
• Pair-view Unsupervised Graph Representation Learning