# shenweichen/GraphEmbedding

Implementation and experiments  of graph embedding algorithms.

Repository: https://github.com/shenweichen/GraphEmbedding
Canonical: https://ross.abutalabs.com/products/graphembedding
Language: Python
License: MIT
License Family: permissive
Topics: deepwalk, node2vec, line, sdne, struc2vec, graph, graphembedding
Last push: 2026-04-26T07:23:36+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 35, longevity 100
- inputs: {"age_days": 2760, "days_push": 129, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3845, forks 995 (observed 2026-08-28T04:08:24.071184+00:00)

## What it is
A Python library providing implementations of classic graph embedding algorithms including DeepWalk, LINE, Node2Vec, SDNE, and Struc2Vec. It includes runnable example scripts for learning node representations from network data.

## Use cases
- generate node embeddings for a graph
- run deepwalk on a network
- learn node2vec representations
- compare graph embedding algorithms
- embed social network nodes for downstream ML
- learn structural node representations with struc2vec

## When to choose
- you need ready-to-use implementations of classic graph embedding algorithms like DeepWalk, LINE, Node2Vec, SDNE, or Struc2Vec
- you want reference implementations with example scripts for learning and experimentation
- you are benchmarking or studying network embedding methods in Python

## When to avoid
- you need large-scale, production-grade distributed graph embedding
- you need modern GNN-based methods like GraphSAGE or GAT
- you need a maintained library with broad ecosystem support outside Python/TensorFlow

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, data-science, graph-processing
- platform: python
- tags: graph-embedding, deepwalk, node2vec, line, sdne, struc2vec, network-embedding, representation-learning, algorithms

## Member repositories
- shenweichen/GraphEmbedding (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:24.071184+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 2026-08-29T18:26:01.902563+00:00, confidence not recorded.
  - readme: https://github.com/shenweichen/GraphEmbedding (fetched 2026-08-28T04:08:24.071184+00:00, sha c96bc4b754fb)
- Data as of 2026-08-30T08:39:29.467469+00:00.