Simplifying Clustering with Graph Neural Networks

Filippo Maria Bianchi
7/18/2022
cs.LG

No official code found. Best implementation: FilippoMB/Simplifying-Clustering-with-Graph-Neural-Networks (38 stars, MIT, last commit 2025-04-28).

Abstract

The objective functions used in spectral clustering are usually composed of two terms: i) a term that minimizes the local quadratic variation of the cluster assignments on the graph and; ii) a term that balances the clustering partition and helps avoiding degenerate solutions. This paper shows that a graph neural network, equipped with suitable message passing layers, can generate good cluster assignments by optimizing only a balancing term. Results on attributed graph datasets show the effectiveness of the proposed approach in terms of clustering performance and computation time.

View on arXivView PDF

Code Implementations(1)

FilippoMB/Simplifying-Clustering-with-Graph-Neural-NetworksCommunity100%
MIT

Implementation of "Just Balance GNN" for graph classification and node clustering from the paper "Simplifying Clusterings with Graph Neural Networks".

385PythonJul 17, 20221 years agoMIT
graph-classificationgraph-clusteringgraph-coarseninggraph-neural-networksgraph-pooling+2 more

Similar Papers

Differentiable Cluster Graph Neural Network

85% match2024

Clustering Node Attributed Networks with Graph Neural Networks and Self Learning

85% match2026

Spectral Clustering with Graph Neural Networks for Graph Pooling

84% match2 repos2782019

Homophily-enhanced Structure Learning for Graph Clustering

83% match1 repo112023

Reinforcement Graph Clustering with Unknown Cluster Number

82% match2 repos1.0k2023

Neural network-based clustering using pairwise constraints

82% match1 repo712015

Cite this paper

@article{bianchi2022simplifying,
  title  = {Simplifying Clustering with Graph Neural Networks},
  author = {Filippo Maria Bianchi},
  year   = {2022},
  eprint = {2207.08779},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.08779v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.08779.svg)](https://codeofpaper.com/paper/2207.08779)

Discussion