This repository provides a TensorFlow implementation of Graph Auto-Encoders (GAEs) and Variational Graph Auto-Encoders, neural network models for unsupervised learning on graph data. The models use graph convolutional layers to learn node embeddings for tasks such as link prediction, clustering, and matrix completion. The implementation builds on Graph Convolutional Networks (GCNs) and supports citation network datasets like Cora, Citeseer, and Pubmed.