emalgorithm/directed-graph-neural-network
Dir-GNN is a machine learning model that enables learning on directed graphs.
This machine learning model helps researchers and data scientists analyze complex, interconnected data where the relationships between items have a specific direction (like citations in a paper network or connections in a social graph). You input a directed graph dataset, and it improves the accuracy of classifying or understanding the nodes within that graph. It's for those working with graph-structured data where relationship directionality matters for insight.
No commits in the last 6 months.
Use this if you are working with directed graph datasets and need to improve the performance of node classification or other graph-based learning tasks by specifically accounting for the direction of connections.
Not ideal if your data relationships are inherently symmetrical and undirected, or if you are not experienced with machine learning model development and experimentation.
Stars
84
Forks
9
Language
Python
License
MIT
Category
Last pushed
Jun 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/emalgorithm/directed-graph-neural-network"
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.