Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation
Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation
复制标题
DOI：
10.1109/tnnls.2023.3339470
复制
发表时间：
2022-12
影响因子：
10.4
通讯作者：
Giorgio Morales;John W. Sheppard
中科院分区：
文献类型：
--
作者：
Giorgio Morales;John W. Sheppard
准确的不确定性量化对于增强深度学习（DL）模型在实际应用中的可靠性是必要的。在回归任务中，预测区间 (PI) 应与 DL 模型的确定性预测一起提供。只要此类 PI 足够窄并捕获大部分概率密度，它们就是有用的或“高质量 (HQ)”。在本文中，除了传统的目标预测之外，我们还提出了一种自动学习基于回归的神经网络 (NN) PI 的方法。特别是，我们训练两个伴随神经网络：一个使用一个输出（目标估计），另一个使用两个输出（相应 PI 的上限和下限）。我们的主要贡献是为 PI 生成网络设计了一种新颖的损失函数，该函数考虑了目标估计网络的输出，并具有两个优化目标：最小化平均 PI 宽度并使用隐式最大化 PI 概率覆盖范围的约束确保 PI 完整性。此外，我们引入了一个自适应系数来平衡损失函数内的两个目标，从而减轻了微调的任务。使用合成数据集、八个基准数据集和真实世界作物产量预测数据集的实验表明，与三种最先进的基于神经网络的方法生成的 PI 相比，我们的方法能够保持名义概率覆盖范围并产生显着更窄的 PI，而不损害其目标估计精度。换句话说，我们的方法被证明可以产生更高质量的 PI。
Accurate uncertainty quantification is necessary to enhance the reliability of deep learning (DL) models in real-world applications. In the case of regression tasks, prediction intervals (PIs) should be provided along with the deterministic predictions of DL models. Such PIs are useful or "high-quality (HQ)" as long as they are sufficiently narrow and capture most of the probability density. In this article, we present a method to learn PIs for regression-based neural networks (NNs) automatically in addition to the conventional target predictions. In particular, we train two companion NNs: one that uses one output, the target estimate, and another that uses two outputs, the upper and lower bounds of the corresponding PI. Our main contribution is the design of a novel loss function for the PI-generation network that takes into account the output of the target-estimation network and has two optimization objectives: minimizing the mean PI width and ensuring the PI integrity using constraints that maximize the PI probability coverage implicitly. Furthermore, we introduce a self-adaptive coefficient that balances both objectives within the loss function, which alleviates the task of fine-tuning. Experiments using a synthetic dataset, eight benchmark datasets, and a real-world crop yield prediction dataset showed that our method was able to maintain a nominal probability coverage and produce significantly narrower PIs without detriment to its target estimation accuracy when compared to those PIs generated by three state-of-the-art neural-network-based methods. In other words, our method was shown to produce higher quality PIs.