Quantifying predictive uncertainty in deep neural networks is a challenging and yet unsolved problem. Existing quantification approaches can be categorized into two lines. Bayesian methods provide a complete uncertainty quantification theory but are often not scalable to large-scale models. Along another line, non-Bayesian methods have good scalability and can quantify uncertainty with high quality. The most remarkable idea in this line is Deep Ensemble, but it is limited in practice due to its expensive computational cost. Thus, we propose HatchEnsemble to improve the efficiency and practicality of Deep Ensemble. The main idea is to use function-preserving transformations, ensuring HatchNets to inherit the knowledge learned by a single model called SeedNet. This process is called hatching, and HatchNet can be obtained by continuously widening the SeedNet. Based on our method, two different hatches are proposed, respectively, for ensembling the same and different architecture networks. To ensure the diversity of models, we also add random noises to parameters during hatching. Experiments on both clean and corrupted datasets show that HatchEnsemble can give a competitive prediction performance and better-calibrated uncertainty quantification in a shorter time compared with baselines.

量化深度神经网络中的预测不确定性是一个具有挑战性但尚未解决的问题。现有的量化方法可以分为两类。贝叶斯方法提供了完整的不确定性量化理论，但通常无法扩展到大规模模型。另一方面，非贝叶斯方法具有良好的可扩展性，可以高质量地量化不确定性。这一行中最引人注目的想法是 Deep Ensemble，但由于其昂贵的计算成本，它在实践中受到限制。因此，我们建议HatchEnsemble提高 Deep Ensemble 的效率和实用性。主要思想是使用功能保留转换，确保 HatchNets 继承由称为 SeedNet 的单个模型学习的知识。这个过程叫做孵化，通过不断拓宽SeedNet就可以得到HatchNet。基于我们的方法，分别提出了两个不同的舱口，用于集成相同和不同的架构网络。为了保证模型的多样性，我们还在孵化过程中给参数添加了随机噪声。在干净和损坏的数据集上进行的实验表明，与基线相比，HatchEnsemble可以在更短的时间内提供具有竞争力的预测性能和更好的校准不确定性量化。