BorgwardtLab/TOGL
Topological Graph Neural Networks (ICLR 2022)
This tool helps machine learning researchers evaluate and improve how their graph neural networks (GNNs) interpret and learn from the structural patterns in data. It takes in datasets represented as graphs (like those from chemistry or social networks) and outputs trained GNN models that incorporate topological information, potentially leading to more robust or accurate predictions. Researchers working with complex network data will find this useful for advancing GNN model performance.
126 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher focused on graph neural networks and want to explore how incorporating topological features can enhance your model's understanding and performance on graph-structured data.
Not ideal if you are looking for an off-the-shelf solution for a specific graph prediction task without a deep interest in the underlying GNN architecture and research.
Stars
126
Forks
28
Language
Python
License
BSD-3-Clause
Category
Last pushed
Jun 10, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BorgwardtLab/TOGL"
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.