Graph Resources

Below is a collection of the top packages, repos, and papers relating to Graphs for ML.

Libraries

• StellarGraph (opens new window): Machine Learning on Graphs.
• NetworkX (opens new window): Network Analysis in Python
• AutoGL (opens new window): An autoML framework & toolkit for machine learning on graphs.
• Node2Vec (opens new window): Implementation of the node2vec algorithm.
• SNAP (opens new window): Stanford Network Analysis Project
• Deep Graph Library (opens new window): Python package built to ease deep learning on graph, on top of existing DL frameworks.

Papers

• Representation Learning on Graphs: Methods and Applications (opens new window): Authors provide a conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph convolutional networks
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy (opens new window): Authors propose a comprehensive taxonomy of representation learning methods for graph-structured data, aiming to unify several disparate bodies of work.
• Online Actions with Offline Impact: How Online Social Networks Influence Online and Offline User Behavior (opens new window): Authors study how social networks influence user behavior in a physical activity tracking application.
• Inductive Representation Learning on Large Graphs (opens new window): GraphSAGE

Books

• The Practitioner's Guide to Graph Data: Applying Graph Thinking and Graph Technologies to Solve Complex Problems by Denise Gosnell
• Graph Representation Learning Book by William L. Hamilton (opens new window)

Articles

• Deep learning on graphs: successes, challenges, and next steps (opens new window)
• Top Applications of Graph Neural Networks 2021 (opens new window)
• Semantic Models for Constructing Knowledge Graphs (opens new window)
• Machine Learning With Graphs (opens new window)