Generative Graph Convolutional Network for Growing Graphs

Abstract

Modeling generative process of growing graphs has wide applications in social networks and recommendation systems, where cold start problem leads to new nodes isolated from existing graph. Despite the emerging literature in learning graph representation and graph generation, most of them can not handle isolated new nodes without nontrivial modifications. The challenge arises due to the fact that learning to generate representations for nodes in observed graph relies heavily on topological features, whereas for new nodes only node attributes are available. Here we propose a unified generative graph convolutional network that learns node representations for all nodes adaptively in a generative model framework, by sampling graph generation sequences constructed from observed graph data. We optimize over a variational lower bound that consists of a graph reconstruction term and an adaptive Kullback-Leibler divergence regularization term. We demonstrate the superior performance of our approach on several benchmark citation network datasets.

References in corpus (10)

• Auto-Encoding Variational Bayes
• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• LINE: Large-scale Information Network Embedding
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Variational Graph Auto-Encoders
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Learning Deep Generative Models of Graphs
• Revisiting Semi-Supervised Learning with Graph Embeddings
• Graphite: Iterative Generative Modeling of Graphs

Cited by in corpus (3)

• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• Local Augmentation for Graph Neural Networks
• Inference for Network Structure and Dynamics from Time Series Data via Graph Neural Network