Community detection with spiking neural networks for neuromorphic hardware

TL;DR

This paper demonstrates a neuromorphic approach to community detection in graphs using spiking neural networks, showing that firing patterns can reveal community structures through event-driven computation.

Contribution

It introduces a novel mapping from graphs to spiking neural systems and shows how firing patterns can be used to identify communities in a neuromorphic hardware context.

Findings

Community detection achieved on a 128-vertex graph

Binary decoding with Hamming distance effectively identifies communities

Inhibitory connections prevent pattern spread, enhancing detection accuracy

Abstract

We present results related to the performance of an algorithm for community detection which incorporates event-driven computation. We define a mapping which takes a graph G to a system of spiking neurons. Using a fully connected spiking neuron system, with both inhibitory and excitatory synaptic connections, the firing patterns of neurons within the same community can be distinguished from firing patterns of neurons in different communities. On a random graph with 128 vertices and known community structure we show that by using binary decoding and a Hamming-distance based metric, individual communities can be identified from spike train similarities. Using bipolar decoding and finite rate thresholding, we verify that inhibitory connections prevent the spread of spiking patterns.