Network Classifiers Based on Social Learning
This work addresses the challenge of enhancing prediction accuracy in streaming data scenarios for machine learning applications, though it appears incremental as it builds on social learning concepts.
The paper tackles the problem of improving classifier performance over time with unlabeled streaming data by proposing a Social Machine Learning paradigm that combines independently trained classifiers over space and time, resulting in consistent learning and robustness against poorly trained classifiers.
This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to streaming data during testing and continue to improve their performance even during this phase. By doing so, the proposed architecture is able to improve prediction performance over time with unlabeled data. Inspired by social learning algorithms, which require prior knowledge of the observations distribution, we propose a Social Machine Learning (SML) paradigm that is able to exploit the imperfect models generated during the learning phase. We show that this strategy results in consistent learning with high probability, and it yields a robust structure against poorly trained classifiers. Simulations with an ensemble of feedforward neural networks are provided to illustrate the theoretical results.