Introduction to graph representation learning, including methods for embedding graph data, graph neural networks, and deep generative models of graphs.

graph-representation-learning graph-neural-networks knowledge-graphs book graphs article embeddings representation-learning

The field of graph representation learning has grown at an incredible (and sometimes unwieldy) pace over the past seven years, transforming from a small subset of researchers working on a relatively niche topic to one of the fastest growing sub-areas of deep learning.

This book is my attempt to provide a brief but comprehensive introduction to graph representation learning, including methods for embedding graph data, graph neural networks, and deep generative models of graphs.

**Contents and Chapter Drafts**

- Chapter 1: Introduction and Motivations
- Chapter 2: Background and Traditional Approaches
- Part I: Node Embeddings
- Chapter 3: Neighborhood Reconstruction Methods
- Chapter 4: Multi-Relational Data and Knowledge Graphs

- Part II: Graph Neural Networks
- Chapter 5: The Graph Neural Network Model
- Chapter 6: Graph Neural Networks in Practice
- Chapter 7: Theoretical Motivations

- Part III: Generative Graph Models
- Chapter 8: Traditional Graph Generation Approaches
- Chapter 9: Deep Generative Models

- Bibliography

Don't forget to tag @williamleif in your comment, otherwise they may not be notified.

Assistant Professor at McGill University and Mila, working on machine learning, NLP, and network analysis.

Graph Nets

2020-02-01 ·
PyTorch Implementation and Explanation of Graph Representation Learning papers involving DeepWalk, GCN, GraphSAGE, ChebNet & GAT.

Geometric and Relational Deep Learning

2020-04-24 ·
Videos from emerging fields of Graph Representation Learning and Geometric Deep Learning.

Latent graph neural networks: Manifold learning 2.0?

2020-09-10 ·
Parallels between recent works on latent graph learning and older techniques of manifold learning.