# Compressing networks with super nodes

## TL;DR

This paper introduces a method to compress large networks into smaller 'super node' networks to improve the efficiency and stability of community detection algorithms, while maintaining accuracy.

## Contribution

The paper presents a novel network compression technique using super nodes based on CoreHD ranking, enhancing community detection speed and stability.

## Key findings

- Community detection on super node networks is significantly faster.
- Partitions on compressed networks are more stable across runs.
- Results closely match those from full network analysis.

## Abstract

Community detection is a commonly used technique for identifying groups in a network based on similarities in connectivity patterns. To facilitate community detection in large networks, we recast the network to be partitioned into a smaller network of 'super nodes', each super node comprising one or more nodes in the original network. To define the seeds of our super nodes, we apply the 'CoreHD' ranking from dismantling and decycling. We test our approach through the analysis of two common methods for community detection: modularity maximization with the Louvain algorithm and maximum likelihood optimization for fitting a stochastic block model. Our results highlight that applying community detection to the compressed network of super nodes is significantly faster while successfully producing partitions that are more aligned with the local network connectivity, more stable across multiple (stochastic) runs within and between community detection algorithms, and overlap well with the results obtained using the full network.