benedekrozemberczki/ClusterGCN
A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019).
This tool helps data scientists and machine learning engineers analyze very large, interconnected datasets by classifying nodes within graphs. You provide an edge list, sparse features for each node, and target labels for some nodes. It then outputs trained models and predictions for unlabeled nodes efficiently, even on massive graphs that would otherwise exceed memory limits.
806 stars. No commits in the last 6 months.
Use this if you need to train graph convolutional networks on extremely large datasets that typically cause out-of-memory errors or very long training times for standard GCN algorithms.
Not ideal if your datasets are small or if you require very fine-grained control over the graph clustering process beyond what's offered by the default methods.
Stars
806
Forks
137
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/ClusterGCN"
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.