#31 · Primary category： Classical Machine Learning Frameworks
node2vec
Implementation of the node2vec algorithm.
Project last updated：10/06/25
GitHub Stars
1.3K
Forks
253
Contributors
16
License
MIT
Why we included this project
Turning a graph into numeric vectors is a common need when you want to feed relationships into a classifier or clustering step. This library implements the node2vec algorithm, which learns node embeddings by simulating biased random walks and training a word2vec-style model on the resulting sequences. You pass in a NetworkX graph, tune a few parameters like walk length and the p and q controls, and get back a gensim model you can query for similar nodes or save for later. It also includes edge embedders for link prediction. The project is in maintenance mode and parallel execution can misbehave on Windows, but for small to medium graph experiments it's still a practical, well-documented starting point.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
scikit-learn
scikit-learn: machine learning in Python
pyod
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
dowhy
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
umap
Uniform Manifold Approximation and Projection
imbalanced-learn
A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning