lmotte/graph-prediction-with-fused-gromov-wasserstein
Python implementation of the supervised graph prediction method proposed in http://arxiv.org/abs/2202.03813 using PyTorch library and POT library (Python Optimal Transport).
This is a Python tool for supervised learning on graphs. It takes in existing labeled graphs (e.g., molecular structures with features) and a target value (e.g., a chemical property) to learn a mapping that can predict new graphs based on new input values. It's designed for researchers or data scientists working with complex, interconnected data where traditional methods struggle with graph comparisons.
No commits in the last 6 months.
Use this if you need to predict entire graph structures, complete with node connections and features, from simple input values, especially when your graphs can vary in size and complexity.
Not ideal if your problem involves simple classification or regression on fixed-size graph properties, rather than predicting the graph structure itself.
Stars
16
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 25, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lmotte/graph-prediction-with-fused-gromov-wasserstein"
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.