gasteigerjo/gtn
Graph transport network (GTN), as proposed in "Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More" (ICML 2021)
This project helps researchers and data scientists compare complex networks or analyze how different datasets relate to each other when they are represented as graphs. You input two graphs or sets of graph-based data, and it outputs a measure of their similarity or an aligned representation. This is useful for anyone working with interconnected data, such as in biology, social sciences, or machine learning research.
No commits in the last 6 months.
Use this if you need to efficiently calculate distances between large graphs or align graph embeddings where traditional methods are too slow.
Not ideal if you are looking for a simple graph visualization tool or a library for basic graph traversal algorithms.
Stars
15
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gasteigerjo/gtn"
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.