论文标题
多域温度缩放的稳健校准
Robust Calibration with Multi-domain Temperature Scaling
论文作者
论文摘要
不确定性量化对于将机器学习模型的可靠部署到高风险应用程序域而言至关重要。当训练分布和测试分布不同时，不确定性量化也更具挑战性，即使分布变化也是轻微的。尽管现实世界应用中分配变化的普遍性，但现有的不确定性量化方法主要研究火车和测试分布相同的分布环境。在本文中，我们开发了一个系统的校准模型，以通过利用来自多个域的数据来处理分布变化。我们提出的方法 - 多域温度缩放 - 使用域中的异质性来改善分布移位下的校准鲁棒性。通过对三个基准数据集的实验，我们发现我们所提出的方法优于现有方法，这些方法均以分布和分发测试集的衡量。
Uncertainty quantification is essential for the reliable deployment of machine learning models to high-stakes application domains. Uncertainty quantification is all the more challenging when training distribution and test distribution are different, even the distribution shifts are mild. Despite the ubiquity of distribution shifts in real-world applications, existing uncertainty quantification approaches mainly study the in-distribution setting where the train and test distributions are the same. In this paper, we develop a systematic calibration model to handle distribution shifts by leveraging data from multiple domains. Our proposed method -- multi-domain temperature scaling -- uses the heterogeneity in the domains to improve calibration robustness under distribution shift. Through experiments on three benchmark data sets, we find our proposed method outperforms existing methods as measured on both in-distribution and out-of-distribution test sets.
