benedekrozemberczki/MixHop-and-N-GCN
A PyTorch and TensorFlow implementation of MixHop and N-GCN graph neural network layers for higher-order graph representation learning.
Not currently ranked — collecting fresh signals.
star history
This repository provides implementations of two graph convolutional architectures: MixHop (ICML 2019) and N-GCN (NeurIPS 2018). MixHop layers mix multiple powers of the adjacency matrix to learn delta operators, while N-GCN provides a higher-order graph convolutional layer. Both implementations maintain the same memory footprint and computational complexity as standard GCN while capturing multi-scale neighborhood information for improved node classification on graph data.
Frequently asked
- What is benedekrozemberczki/MixHop-and-N-GCN?
- A PyTorch and TensorFlow implementation of MixHop and N-GCN graph neural network layers for higher-order graph representation learning.
- Is MixHop-and-N-GCN open source?
- Yes — benedekrozemberczki/MixHop-and-N-GCN is open source, released under the GPL-3.0 license.
- What language is MixHop-and-N-GCN written in?
- benedekrozemberczki/MixHop-and-N-GCN is primarily written in Python.
- How popular is MixHop-and-N-GCN?
- benedekrozemberczki/MixHop-and-N-GCN has 406 stars on GitHub.
- Where can I find MixHop-and-N-GCN?
- benedekrozemberczki/MixHop-and-N-GCN is on GitHub at https://github.com/benedekrozemberczki/MixHop-and-N-GCN.