Ensemble Clustering for Graphs

Valérie Poulin, François Théberge
9/14/2018
cs.LGcs.SIstat.ML

Official code: ftheberge/graph-partition-and-measures (30 stars, MIT, last commit 2026-07-02).

Abstract

We propose an ensemble clustering algorithm for graphs (ECG), which is based on the Louvain algorithm and the concept of consensus clustering. We validate our approach by replicating a recently published study comparing graph clustering algorithms over artificial networks, showing that ECG outperforms the leading algorithms from that study. We also illustrate how the ensemble obtained with ECG can be used to quantify the presence of community structure in the graph.

View on arXivView PDF

Code Implementations(1)

ftheberge/graph-partition-and-measuresOfficial100%
MIT

Python code implementing a stable ensemble-based graph partition algorithm (ecg) and 11 graph-aware measures (gam) for comparing graph partitions.

301Python, Jupyter NotebookApr 22, 20203 months agoMIT

Similar Papers

Ensemble Clustering for Graphs: Comparisons and Applications

96% match1 repo302019

Spectral Clustering with Graph Neural Networks for Graph Pooling

87% match2 repos2782019

Hierarchical Graph Clustering using Node Pair Sampling

85% match2 repos382018

Clustering Node Attributed Networks with Graph Neural Networks and Self Learning

85% match2026

A Clustering Method with Graph Maximum Decoding Information

84% match2024

Similarity and Dissimilarity Guided Co-association Matrix Construction for Ensemble Clustering

84% match1 repo42024

Cite this paper

@article{poulin2018ensemble,
  title  = {Ensemble Clustering for Graphs},
  author = {Valérie Poulin and François Théberge},
  year   = {2018},
  eprint = {1809.05578},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1809.05578}
}

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/1809.05578.svg)](https://codeofpaper.com/paper/1809.05578)

Discussion