aditya-grover/node2vec

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2739 stars · 906 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Reference implementation of the node2vec algorithm for learning continuous low-dimensional node representations from arbitrary (un)directed, (un)weighted graphs via biased random walks. It outputs embeddings usable as features for downstream machine learning tasks.

Use cases

• learn node embeddings from a graph
• generate features for network machine learning
• detect communities in a network
• embed a social graph for classification
• run node2vec on an edgelist
• graph representation learning for link prediction

When to choose

• you need the original reference implementation of node2vec for research or citation
• you have graph data in edgelist format and want node feature vectors
• you want to balance homophily vs structural equivalence via p and q parameters

When to avoid

• you need high performance on very large graphs - use the SNAP C++ implementation instead
• you need actively maintained code with modern Python packaging
• you want deep graph neural networks rather than random-walk embeddings

Facets

library · maturity maintenance

machine-learning data-science machine-learning graph-processing python cross-platform graph-embeddings node2vec network-embedding random-walks snap algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aditya-grover/node2vec")