Classification with a Network of Partially Informative Agents: Enabling Wise Crowds from Individually Myopic Classifiers
Abstract: 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.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: We have highlighted the changes in the revision.
- Restructured Problem formulation Sec 2.1 to clarify the agent's knowledge and network topology.
- Added examples and motivations in the Introduction.
- Revised comparisons in Related Literature: Distributed non-Bayesian social learning.
- Updated Figure 1.
- Provided a short introduction to Sec 3.1.
- Added comparisons to Mitra et al. in Sec 3.2.
- Added a demonstration example in Sec 5.1.
- Clarified $\theta$ in Theorem 4.2.
Assigned Action Editor: ~Andras_Gyorgy1
Submission Number: 813
Loading