Variational Graph Auto-Encoders

Abstract

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.

Bayesian Deep Learning Workshop (NIPS 2016)

References in corpus (1)

• Semi-Supervised Classification with Graph Convolutional Networks

Cited by in corpus (28)

• Fast Graph Representation Learning with PyTorch Geometric
• Graph Convolutional Matrix Completion
• Representation Learning for Attributed Multiplex Heterogeneous Network
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Compositional Fairness Constraints for Graph Embeddings
• Explainability Techniques for Graph Convolutional Networks
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• Attributed Graph Clustering: A Deep Attentional Embedding Approach
• Graph Normalizing Flows
• All SMILES Variational Autoencoder
• Spectral-based Graph Convolutional Network for Directed Graphs
• A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks
• Attributed Graph Clustering via Adaptive Graph Convolution
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• Deep Representation Learning for Social Network Analysis
• Towards Probabilistic Generative Models Harnessing Graph Neural Networks for Disease-Gene Prediction
• Stability and Generalization of Graph Convolutional Neural Networks
• Generative Graph Convolutional Network for Growing Graphs
• RepGN:Object Detection with Relational Proposal Graph Network
• Context-Aware Visual Compatibility Prediction
• Network Representation Learning: Consolidation and Renewed Bearing
• Tiered Latent Representations and Latent Spaces for Molecular Graphs
• Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference
• Representation Learning on Graphs: A Reinforcement Learning Application
• Graph Embeddings at Scale
• Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Node Attribute Generation on Graphs