benedekrozemberczki/PDN
The official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
This project helps researchers and data scientists analyze complex network data, such as social networks, biological networks, or citation networks. It takes an existing network, node characteristics, and target classifications as input and produces an improved understanding of how information flows through the network, along with more accurate predictions for node classifications. Its users are researchers or data scientists working with interconnected data.
Use this if you need to build more accurate predictive models on networked data and want to understand the hidden connections driving those predictions.
Not ideal if your data is not structured as a network or you require real-time model training and inference.
Stars
59
Forks
11
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/PDN"
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.