Classification with a Network of Partially Informative Agents: Enabling Wise Crowds from Individually Myopic Classifiers
This addresses distributed classification for networks with heterogeneous agents, offering a method to aggregate partial information, though it appears incremental as it builds on existing belief propagation and consensus techniques.
The paper tackles classification in a network of agents with limited local classifiers, proposing an iterative algorithm that updates beliefs using local signals and neighbor information to converge to the true class. It shows asymptotic convergence with a provided rate and demonstrates performance on image data using random forest and MobileNet classifiers.
We consider the problem of classification with a (peer-to-peer) network of heterogeneous and partially informative agents, each receiving local data generated by an underlying true class, and equipped with a classifier that can only distinguish between a subset of the entire set of classes. We propose an iterative algorithm that uses the posterior probabilities of the local classifier and recursively updates each agent's local belief on all the possible classes, based on its local signals and belief information from its neighbors. We then adopt a novel distributed min-rule to update each agent's global belief and enable learning of the true class for all agents. We show that under certain assumptions, the beliefs on the true class converge to one asymptotically almost surely. We provide the asymptotic convergence rate, and demonstrate the performance of our algorithm through simulation with image data and experimented with random forest classifiers and MobileNet.