benedekrozemberczki/GraphWaveletNeuralNetwork
A PyTorch implementation of "Graph Wavelet Neural Network" (ICLR 2019)
This project helps researchers and data scientists classify nodes within a network, like categorizing academic papers based on their citation graph or users in a social network. You provide a list of connections between items (an 'edge list'), some characteristics for each item (a 'feature matrix'), and existing categories for a portion of them. The output is a classification for the remaining unlabelled items in the network.
605 stars. No commits in the last 6 months.
Use this if you need to classify items in a network where connections between items are as important as their individual characteristics.
Not ideal if your data isn't structured as a graph or if you require a classification method that doesn't rely on network topology.
Stars
605
Forks
119
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/GraphWaveletNeuralNetwork"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.