Diversity Learning: Introducing the Space-time Scheme to Ensemble Learning

Inspired by diversity technology, we rethink the model enhancement from the view of wireless communication and propose a space-time framework for ensemble learning, called diversity learning. Such framework provides a new perspective that links the multi-model learning with the multi-channel communication. In this paper, 2x1 diversity learning is mainly studied whose efficiency is guaranteed theoretically. We also evaluate the proposed scheme on two popular image classification tasks, MNIST and CIFAR-10. The results elucidate that the diversity learning reaps superiority on model enhancement, convergence, complexity and robustness compared to single models as well as weighting ensemble approach. Furthermore, the diversity schemes can be deployed in several emerging distributed learning systems, especially the mobile scenarios such as edge computing and cooperative learning where the resources for computation and communication are restricted.