danielzuegner/netgan
Implementation of the paper "NetGAN: Generating Graphs via Random Walks".
This tool helps researchers and data scientists generate realistic synthetic graph data. You provide it with an existing graph, and it learns to produce new, similar graphs. It can be used by data scientists, researchers, or anyone needing to expand or simulate network structures for analysis or testing.
198 stars. No commits in the last 6 months.
Use this if you need to create synthetic networks that mimic the structural properties of real-world graphs, especially for tasks like privacy-preserving data sharing or augmenting datasets.
Not ideal if you need to analyze or visualize existing graphs, or if your data is not structured as a network.
Stars
198
Forks
67
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 07, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danielzuegner/netgan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.