In machine learning, it is observed that probabilistic predictions sometimes disagree with averaged actual outcomes on certain subsets of data. This is also known as miscalibration that is responsible for unreliability and unfairness of practical machine learning systems. In this paper, we put forward an evaluation metric for calibration, coined field-level calibration error, that measures bias in predictions over the input fields that the decision maker concerns. We show that existing calibration methods perform poorly under our new metric. Specifically, after learning a calibration mapping over the validation dataset, existing methods have limited improvements in our error metric and completely fail to improve other non-calibration metrics such as the AUC score. We propose Neural Calibration, a new calibration method, which learns to calibrate by making full use of all input information over the validation set. We test our method on five large-scale real-world datasets. The results show that Neural Calibration significantly improves against uncalibrated predictions in all well-known metrics such as the negative log-likelihood, the Brier score, the AUC score, as well as our proposed field-level calibration error.

本文提出了一种新的评估指标，称为“field-level calibration error”，用于衡量决策者关注的敏感输入领域中预测偏差，提出了一种名为神经校准的后续校准方法，使用验证集中的领域感知信息进行校准，并通过实验证明其对常见度量（如负对数似然、布里尔分数和AUC）以及所提出的“field-level calibration error”指标的校准性能得到了显著提高。

Field-aware Calibration：可靠概率预测的简单有效方法