guoji-fu/pGNNs

[ICML 2022] pGNN, p-Laplacian Based Graph Neural Networks

39
/ 100
Emerging

This project provides an implementation of p-Laplacian Based Graph Neural Networks, a specialized machine learning model for analyzing data structured as graphs. It takes graph-structured data (like networks of connections) and outputs classifications or predictions based on the relationships within that data. This is primarily for machine learning researchers and practitioners who develop and test advanced graph-based algorithms.

No commits in the last 6 months.

Use this if you are a machine learning researcher working with graph-structured data and need to implement or benchmark a specific type of graph neural network from a published academic paper.

Not ideal if you are looking for an off-the-shelf solution for general graph analysis, as this requires familiarity with machine learning frameworks and academic concepts.

graph-data-analysis machine-learning-research network-science academic-benchmarking deep-learning-models
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

27

Forks

5

Language

Python

License

MIT

Last pushed

Aug 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/guoji-fu/pGNNs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.