#222222nd of 242 in ML frameworks and libraries
graphembedding
Python graph embedding library: DeepWalk, LINE, Node2Vec, SDNE, Struc2Vec
- Stars
- 3.8k
- License
- MIT
- Last commit
- Apr 2026
- Language
- Python
3,821 on 25 Apr 20263,841 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Python library that learns node embeddings from a networkx graph, following a "graph in, embedding out" design. It implements five published methods: DeepWalk, LINE, Node2Vec, SDNE and Struc2Vec. Each model is initialised with a graph, trained with train(), and returns vectors through get_embeddings().
Who it is for: Python users computing node embeddings on graphs for research or recommendation
Strengths
- Five classic embedding methods share one init/train/get_embeddings interface
- Reads plain networkx graphs from edge-list files, with optional edge weights
- Example scripts included, run after pip install -e .[tf]
- MIT license
Weaknesses
- No tagged release; install is from a cloned repo only
- Covers only 2014-2017 methods; no GNN-based or newer embedding models
- Docs are README snippets; linked method write-ups are in Chinese
What it needs
- Needs networkx, TensorFlow (tf extra)
- Models: DeepWalk, LINE, Node2Vec, SDNE, Struc2Vec
Also in ML frameworks and libraries
See all 242| Rank | Project | Score |
|---|---|---|
| 1 | transformersModel-definition library for pretrained text, vision, audio and multimodal models | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 94 out of 100 |
| #4 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |