AEGCN: An Autoencoder-Constrained Graph Convolutional Network

Abstract

We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network operating directly on graphs, whose hidden layers are constrained by an autoencoder. Comparing with vanilla graph convolutional networks, the autoencoder step is added to reduce the information loss brought by Laplacian smoothing. We consider applying our model on both homogeneous graphs and heterogeneous graphs. For homogeneous graphs, the autoencoder approximates to the adjacency matrix of the input graph by taking hidden layer representations as encoder and another one-layer graph convolutional network as decoder. For heterogeneous graphs, since there are multiple adjacency matrices corresponding to different types of edges, the autoencoder approximates to the feature matrix of the input graph instead, and changes the encoder to a particularly designed multi-channel pre-processing network with two layers. In both cases, the error occurred in the autoencoder approximation goes to the penalty term in the loss function. In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks. Further, we notice that our technique can be applied on graph attention network to improve the performance as well. This reveals the wide applicability of the proposed autoencoder technique.

arXiv comment23 pages, 4 figures

References in corpus (25)

• Efficient Estimation of Word Representations in Vector Space
• Modularity and community structure in networks
• Community detection in graphs
• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• LINE: Large-scale Information Network Embedding
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Graph Neural Networks: A Review of Methods and Applications
• Simplifying Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Representation Learning on Graphs with Jumping Knowledge Networks
• Variational Graph Auto-Encoders
• The Anatomy of the Facebook Social Graph
• PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• Graph Transformer Networks
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Gated Graph Sequence Neural Networks
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Efficiently Summarising Event Sequences with Rich Interleaving Patterns
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Semi-Implicit Graph Variational Auto-Encoders
• Signed Graph Convolutional Network
• Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learning
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees

Cited by in corpus (2)

• PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies
• Whole-Graph Representation Learning For the Classification of Signed Networks