Learning Graph Representations with Embedding Propagation

Abstract

We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels. With significantly fewer parameters and hyperparameters an instance of EP is competitive with and often outperforms state of the art unsupervised and semi-supervised learning methods on a range of benchmark data sets.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Link Prediction in Complex Networks: A Survey
• A Review of Relational Machine Learning for Knowledge Graphs
• Gated Graph Sequence Neural Networks

Cited by in corpus (12)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Graph Capsule Convolutional Neural Networks
• Context-Dependent Diffusion Network for Visual Relationship Detection
• A Contrastive Variational Graph Auto-Encoder for Node Clustering
• Multi-View Collaborative Network Embedding
• Walk-Steered Convolution for Graph Classification
• Stability and Generalization of Graph Convolutional Neural Networks
• Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network
• Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
• A Graph Convolutional Network Composition Framework for Semi-supervised Classification
• Interferometric Graph Transform for Community Labeling