Spiking label propagation for community detection

TL;DR

This paper introduces a novel community detection method using spike-based label propagation in graphs, leveraging neuromorphic hardware and neural computing principles, without extensive pre-training.

Contribution

It presents a new spike-based label propagation algorithm for community detection that integrates neuromorphic computing and spike responses, avoiding extensive pre-training.

Findings

Effective on graphs with 128 vertices

Works with both homogeneous and heterogeneous communities

Potential for neuromorphic hardware implementation

Abstract

In this paper we present results from a method of community detection using label propagation in undirected, unweighted graphs which incorporates elements of neural computing and spike-based data. Using a fully connected, edge-weighted system of spiking neurons driven by external currents, we generate spike responses that are decoded into a binary signal. The similarity between pairs of signals is quantified using a Hamming-distance based metric and is used to classify vertices into communities. We test our approach on a set of graph instances, each with 128 vertices and either homogeneous or heterogeneous community size distributions. We present our method as a candidate for a split-computing workflow that incorporates neuromorphic hardware and does not require extensive pre-training of network parameters.