On the Influence of Informed Agents on Learning and Adaptation over Networks

TL;DR

This paper investigates how the proportion and distribution of informed agents affect the learning speed and accuracy in adaptive networks, revealing trade-offs and the importance of uninformed agents in steady-state performance.

Contribution

It provides a theoretical analysis of the impact of informed and uninformed agents on network learning, including derived expressions and simulations for complex network models.

Findings

Faster convergence with more informed agents, but with reduced steady-state accuracy.

Uninformed agents significantly influence the network's steady-state performance.

Optimal distribution of informed and uninformed agents depends on desired trade-offs.

Abstract

Adaptive networks consist of a collection of agents with adaptation and learning abilities. The agents interact with each other on a local level and diffuse information across the network through their collaborations. In this work, we consider two types of agents: informed agents and uninformed agents. The former receive new data regularly and perform consultation and in-network tasks, while the latter do not collect data and only participate in the consultation tasks. We examine the performance of adaptive networks as a function of the proportion of informed agents and their distribution in space. The results reveal some interesting and surprising trade-offs between convergence rate and mean-square performance. In particular, among other results, it is shown that the performance of adaptive networks does not necessarily improve with a larger proportion of informed agents. Instead, it is established that the larger the proportion of informed agents is, the faster the convergence rate of the network becomes albeit at the expense of some deterioration in mean-square performance. The results further establish that uninformed agents play an important role in determining the steady-state performance of the network, and that it is preferable to keep some of the highly connected agents uninformed. The arguments reveal an important interplay among three factors: the number and distribution of informed agents in the network, the convergence rate of the learning process, and the estimation accuracy in steady-state. Expressions that quantify these relations are derived, and simulations are included to support the theoretical findings. We further apply the results to two models that are widely used to represent behavior over complex networks, namely, the Erdos-Renyi and scale-free models.