重加权损失提升模型校准，通过低置信度区域优化实现更好可靠性
Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss
- 基于置信度函数的重加权策略，聚焦低置信区域改进校准
- 在多个数据集与模型上达到竞争性校准效果，误差显著降低
- 适用于对预测可靠性要求高的场景，如医疗诊断与自动驾驶
若干重加权风险函数变体，如焦点损失、逆焦点损失和风险覆盖率曲线下面积（AURC），已被提出用于改善模型校准，但其与校准误差之间的理论联系仍不明确。本文重新审视一类广义的加权风险函数，发现校准误差与选择性分类之间存在原则性关联。结果表明，最小化校准误差与选择性分类范式密切相关，优化低置信度区域的选择性风险可自然提升校准性能。所提损失函数虽与双焦点损失共享相似重加权机制，但通过选择不同的置信度评分函数（CSFs）提供更大灵活性。此外，该方法采用基于分箱的累积分布函数（CDF）近似，支持高效梯度优化，复杂度为O(nM)，其中n为样本数，M为分箱数。实证评估显示，该方法在多种数据集和模型架构下均取得具有竞争力的校准性能。
原文摘要 · Abstract (English)
Several variants of reweighted risk functionals, such as focal loss, inverse focal loss, and the Area Under the Risk Coverage Curve (AURC), have been proposed for improving model calibration; yet their theoretical connections to calibration errors remain under-explored. In this paper, we revisit a broad class of weighted risk functions and find a principled connection between calibration error and selective classification. We show that minimizing calibration error is closely linked to the selective classification paradigm and demonstrate that optimizing selective risk in low confidence regions naturally improves calibration. Our proposed loss shares a similar reweighting strategy with dual focal loss but offers greater flexibility through the choice of confidence score functions (CSFs). Furthermore, our approach utilizes a bin-based cumulative distribution function (CDF) approximation, enabling efficient gradient-based optimization with O(nM) complexity for n samples and M bins. Empirical evaluations demonstrate that our method achieves competitive calibration performance across a range of datasets and model architectures.
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。