SherylHYX/pytorch_geometric_signed_directed
PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.
This library provides tools for working with signed and directed graphs, which are networks where connections can have a positive or negative relationship, and flow in a specific direction. It helps researchers and data scientists analyze complex network data, taking in raw graph data and outputting insights for tasks like node classification, link prediction, and node clustering.
146 stars. No commits in the last 6 months.
Use this if you are a researcher or data scientist working with signed or directed graph data and need to apply advanced graph neural network models for analysis.
Not ideal if you are a business user looking for a no-code solution for general graph analysis, or if your network data does not involve signed or directed relationships.
Stars
146
Forks
21
Language
Python
License
MIT
Category
Last pushed
Feb 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SherylHYX/pytorch_geometric_signed_directed"
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.