leowyy/GraphTSNE
PyTorch Implementation of GraphTSNE, ICLR’19
This tool helps researchers and analysts understand complex relationships within graph-structured data, like citation networks or social graphs, by creating intuitive visual representations. It takes information about connections between items (nodes) and their individual characteristics (node features), then produces an interactive 2D map where similar items are clustered together. Data scientists and machine learning researchers working with network analysis will find this useful for exploring their datasets.
137 stars. No commits in the last 6 months.
Use this if you need to visualize large, complex graph datasets to identify patterns, clusters, or anomalies that are hard to spot in raw data.
Not ideal if your data is not structured as a network or if you primarily need statistical metrics rather than a visual overview.
Stars
137
Forks
22
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 27, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leowyy/GraphTSNE"
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.