Noisy Deep Ensemble: Accelerating Deep Ensemble Learning via Noise Injection
This work addresses the computational inefficiency of ensemble training for deep learning practitioners, offering a faster alternative with competitive performance.
The paper tackles the high training time of neural network ensembles by proposing the Noisy Deep Ensemble method, which perturbs a converged parent model's weights to create child models, achieving test accuracy comparable to standard ensembles on CIFAR-10 and CIFAR-100 datasets while significantly reducing training time.
Neural network ensembles is a simple yet effective approach for enhancing generalization capabilities. The most common method involves independently training multiple neural networks initialized with different weights and then averaging their predictions during inference. However, this approach increases training time linearly with the number of ensemble members. To address this issue, we propose the novel ``\textbf{Noisy Deep Ensemble}'' method, significantly reducing the training time required for neural network ensembles. In this method, a \textit{parent model} is trained until convergence, and then the weights of the \textit{parent model} are perturbed in various ways to construct multiple \textit{child models}. This perturbation of the \textit{parent model} weights facilitates the exploration of different local minima while significantly reducing the training time for each ensemble member. We evaluated our method using diverse CNN architectures on CIFAR-10 and CIFAR-100 datasets, surpassing conventional efficient ensemble methods and achieving test accuracy comparable to standard ensembles. Code is available at \href{https://github.com/TSTB-dev/NoisyDeepEnsemble}{https://github.com/TSTB-dev/NoisyDeepEnsemble}