# eliorc/node2vec

Implementation of the node2vec algorithm.

Repository: https://github.com/eliorc/node2vec
Canonical: https://ross.abutalabs.com/products/eliorc-node2vec
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning-algorithms, embeddings, deep-learning
Last push: 2025-10-06T17:29:00+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 45, release rhythm 8, longevity 100
- inputs: {"age_days": 3190, "days_push": 331, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1301, forks 253 (observed 2026-08-28T04:04:17.686623+00:00)

## What it is
A Python library implementing the node2vec algorithm for learning low-dimensional embeddings of nodes and edges in graphs. It integrates with networkx for graph input and gensim Word2Vec for training, supporting weighted graphs and parallel walk generation.

## Use cases
- generate node embeddings for a networkx graph
- embed edges of a graph using the Hadamard method
- find nodes most similar to a given node in a network
- train node2vec on a weighted graph
- save node embeddings in word2vec format for downstream ML tasks

## When to choose
- you need node or edge embeddings from a graph for machine learning tasks
- your graphs are already in networkx format
- you want a pip-installable, well-tested implementation of the node2vec paper

## When to avoid
- you need active maintenance or timely bug fixes - the maintainer has stated they no longer have time
- you need GPU acceleration or very large-scale graph embedding
- you are on Windows and need multi-worker parallelism - only workers=1 is supported

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, rag
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: node2vec, graph-embeddings, network-embeddings, networkx, gensim, word2vec, graph-representation-learning, random-walks, algorithms

## Member repositories
- eliorc/node2vec (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:17.686623+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:52:14.755143+00:00, confidence not recorded.
  - readme: https://github.com/eliorc/node2vec (fetched 2026-08-28T04:04:17.686623+00:00, sha faccc0c557f8)
  - registry_pypi: https://pypi.org/pypi/node2vec/json (fetched 2026-08-29T12:09:43.140472+00:00, sha d5bde6d618fe)
- Data as of 2026-08-30T08:39:29.467469+00:00.