The Impact of Network Connectivity on Collective Learning

TL;DR

This paper investigates how the structure of underlying networks affects collective learning in decentralized systems, showing that less connected and more regular networks can outperform fully connected ones in accuracy.

Contribution

It provides a simulation-based analysis demonstrating the impact of network topology on collective learning performance, challenging the assumption that total connectivity is optimal.

Findings

Totally-connected networks have higher average error.

High regularity networks outperform random connectivity networks.

Network structure significantly influences collective learning accuracy.

Abstract

In decentralised autonomous systems it is the interactions between individual agents which govern the collective behaviours of the system. These local-level interactions are themselves often governed by an underlying network structure. These networks are particularly important for collective learning and decision-making whereby agents must gather evidence from their environment and propagate this information to other agents in the system. Models for collective behaviours may often rely upon the assumption of total connectivity between agents to provide effective information sharing within the system, but this assumption may be ill-advised. In this paper we investigate the impact that the underlying network has on performance in the context of collective learning. Through simulations we study small-world networks with varying levels of connectivity and randomness and conclude that totally-connected networks result in higher average error when compared to networks with less connectivity. Furthermore, we show that networks of high regularity outperform networks with increasing levels of random connectivity.