通过噪声扰动权重，快速构建高效神经网络集成模型
Noisy Deep Ensemble: Accelerating Deep Ensemble Learning via Noise Injection
- 先训练一个主模型，再通过多种方式扰动其权重生成多个子模型
- 在CIFAR-10/100上达到与标准集成相当的测试准确率
- 显著缩短训练时间，适合需要快速部署高泛化模型的场景
神经网络集成是一种简单有效的提升泛化能力的方法。传统方法需独立训练多个随机初始化的模型并平均预测结果，但训练时间随集成数量线性增长。为此，本文提出新颖的「噪声深度集成」方法，显著降低集成训练时间。该方法先将一个主模型训练至收敛，再通过多种方式扰动其权重，生成多个子模型。这种权重扰动机制使子模型探索不同局部最优解，同时大幅减少每个成员的训练开销。我们在CIFAR-10和CIFAR-100数据集上使用多种CNN架构验证了该方法，性能优于现有高效集成方法，且测试准确率接近标准集成。代码已开源。
原文摘要 · Abstract (English)
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}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。