benedekrozemberczki/MixHop-and-N-GCN
An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).
This project helps researchers and data scientists analyze complex relationships within connected data, like citation networks or social graphs. You provide an edge list of connections, along with sparse features and target classes for each node. The project then classifies nodes within the graph, for example, categorizing academic papers or identifying communities.
407 stars. No commits in the last 6 months.
Use this if you need to classify nodes in a graph-structured dataset and are looking for advanced graph convolutional neural network models to achieve state-of-the-art results.
Not ideal if your data is not naturally represented as a graph, or if you prefer a simpler, less specialized classification approach.
Stars
407
Forks
57
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/MixHop-and-N-GCN"
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.