# thunlp/OpenNE

An Open-Source Package for Network Embedding (NE)

Repository: https://github.com/thunlp/OpenNE
Canonical: https://ross.abutalabs.com/products/openne
Language: Python
License: MIT
License Family: permissive
Topics: network-embedding
Last push: 2024-01-10T11:53:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3251, "days_push": 966, "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 1706, forks 482 (observed 2026-08-28T04:05:24.901506+00:00)

## What it is
OpenNE is an open-source Python toolkit for network embedding (graph representation learning) that unifies training and testing interfaces for classic NE models like DeepWalk, LINE, node2vec, GraRep, GCN, and TADW. It implements models on TensorFlow to support GPU training and includes evaluation on node classification tasks.

## Use cases
- learn node embeddings for a graph dataset
- train deepwalk or node2vec on an edgelist
- compare network embedding models on node classification
- incorporate node text attributes into graph embeddings with TADW
- reproduce results from network embedding papers
- generate graph features for downstream machine learning tasks

## When to choose
- you need a unified interface to many classic network embedding algorithms
- you want to benchmark NE models with standard node classification evaluation
- you need text-attributed network embedding via TADW
- you want GPU-accelerated training of NE models via TensorFlow

## When to avoid
- you need modern graph neural network frameworks with dynamic or heterogeneous graph support
- you prefer PyTorch-based tooling like PyTorch Geometric or DGL
- your project requires actively maintained software with recent updates
- you need large-scale distributed graph embedding beyond the scope of this toolkit

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-science, cli
- domain: machine-learning, developer-tools
- platform: python
- tags: network-embedding, graph-embeddings, node2vec, deepwalk, graph-representation-learning, tensorflow, algorithms, linux, macos

## Member repositories
- thunlp/OpenNE (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.901506+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 2026-08-30T03:37:30.544665+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/OpenNE (fetched 2026-08-28T04:05:24.901506+00:00, sha 737e81a6dcee)
- Data as of 2026-08-30T08:39:29.467469+00:00.