Emergent specialization from participation dynamics and multi-learner retraining

TL;DR

This paper analyzes participation dynamics in data-driven online services, showing that risk-reducing behaviors lead to stable, segmented equilibria and that multiple learners with myopic updates can outperform traditional risk minimization.

Contribution

It introduces a general framework for risk-reducing participation dynamics and demonstrates that such dynamics naturally lead to stable, segmented equilibria with improved outcomes for multiple learners.

Findings

Stable equilibria are segmented with sub-populations assigned to single learners.

Repeated myopic updates with multiple learners outperform traditional risk minimization.

Simulated examples from real data illustrate the theoretical phenomena.

Abstract

Numerous online services are data-driven: the behavior of users affects the system's parameters, and the system's parameters affect the users' experience of the service, which in turn affects the way users may interact with the system. For example, people may choose to use a service only for tasks that already works well, or they may choose to switch to a different service. These adaptations influence the ability of a system to learn about a population of users and tasks in order to improve its performance broadly. In this work, we analyze a class of such dynamics -- where users allocate their participation amongst services to reduce the individual risk they experience, and services update their model parameters to reduce the service's risk on their current user population. We refer to these dynamics as \emph{risk-reducing}, which cover a broad class of common model updates including gradient descent and multiplicative weights. For this general class of dynamics, we show that asymptotically stable equilibria are always segmented, with sub-populations allocated to a single learner. Under mild assumptions, the utilitarian social optimum is a stable equilibrium. In contrast to previous work, which shows that repeated risk minimization can result in (Hashimoto et al., 2018; Miller et al., 2021), we find that repeated myopic updates with multiple learners lead to better outcomes. We illustrate the phenomena via a simulated example initialized from real data.