SINr-Embeddings/sinr
The SINr approach to train interpretable word and graph embeddings
This tool helps researchers and data scientists understand the relationships between words or elements in a network. It takes in large text collections or complex network structures and produces 'interpretable embeddings'—numerical representations that clearly show how each word or element connects to specific concepts or communities. This allows users to easily see why the system linked certain items together.
Available on PyPI.
Use this if you need to understand the underlying structure and connections within a large body of text or a complex network, and you want to clearly see why certain elements are grouped together or how they relate to specific themes.
Not ideal if your primary goal is simply to generate compact, high-performance embeddings without needing to directly interpret the meaning of each dimension.
Stars
20
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Dependencies
14
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SINr-Embeddings/sinr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.