https://github.com/alexander-belyi/gnns
GNN-style algorithm for community detection
https://github.com/alexander-belyi/gnns
community-detection gnns modularity network-analysis
Last synced: over 1 year ago
JSON representation
GNN-style algorithm for community detection
- Host: GitHub
- URL: https://github.com/alexander-belyi/gnns
- Owner: Alexander-Belyi
- License: gpl-3.0
- Created: 2022-06-29T18:30:36.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-06-30T16:26:39.000Z (almost 4 years ago)
- Last Synced: 2025-02-27T09:37:21.772Z (over 1 year ago)
- Topics: community-detection, gnns, modularity, network-analysis
- Language: Jupyter Notebook
- Homepage:
- Size: 6.89 MB
- Stars: 6
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# GNNS
This repo is the authors' implementation of the GNN-style algorithm for community detection described in the paper
"[Graph Neural Network Inspired Algorithm for Unsupervised Network Community Detection](https://arxiv.org/abs/2103.02520)".
This paper proposes a new variant of the recurrent graph neural network algorithm for unsupervised network _community detection through modularity optimization_. The new algorithm's performance is compared against state-of-the-art methods. The approach also serves as a proof-of-concept for the broader application of recurrent graph neural networks to unsupervised network optimization.
[GNNS.ipynb](https://github.com/Alexander-Belyi/GNNS/blob/master/GNNS.ipynb) notebook is ready to be run in Google Colab. Just follow the link:
https://colab.research.google.com/github/Alexander-Belyi/GNNS/blob/master/GNNS.ipynb.
It should reproduce the results presented in the paper (enable the GPU backend to reproduce the running time figures).
If you find this work useful, please, consider citing:
```
S. Sobolevsky, A. Belyi, "Graph Neural Network Inspired Algorithm for Unsupervised Network Community Detection" arXiv preprint arXiv:2103.02520
```