Strategic Usage in a Multi-Learner Setting
This addresses the challenge of strategic interactions in multi-learner settings, which is incremental as it extends prior single-service research to dynamic systems.
The paper tackles the problem of strategic user behavior in multi-service systems where users choose services to achieve positive classifications, and services aim to minimize loss functions. It shows that naive retraining can cause oscillations, but using memory in retraining ensures convergence for certain loss classes, with results validated on synthetic and real-world data.
Real-world systems often involve some pool of users choosing between a set of services. With the increase in popularity of online learning algorithms, these services can now self-optimize, leveraging data collected on users to maximize some reward such as service quality. On the flipside, users may strategically choose which services to use in order to pursue their own reward functions, in the process wielding power over which services can see and use their data. Extensive prior research has been conducted on the effects of strategic users in single-service settings, with strategic behavior manifesting in the manipulation of observable features to achieve a desired classification; however, this can often be costly or unattainable for users and fails to capture the full behavior of multi-service dynamic systems. As such, we analyze a setting in which strategic users choose among several available services in order to pursue positive classifications, while services seek to minimize loss functions on their observations. We focus our analysis on realizable settings, and show that naive retraining can still lead to oscillation even if all users are observed at different times; however, if this retraining uses memory of past observations, convergent behavior can be guaranteed for certain loss function classes. We provide results obtained from synthetic and real-world data to empirically validate our theoretical findings.