提出ρ-范数校准法，缓解模型置信度过度放大问题。
Parametric $ρ$-Norm Scaling Calibration
- 引入参数化ρ-范数后处理校准，扩展校准表达式。
- 在有限数据下显著提升不确定性校准效果，保持准确率。
- 加入分布正则化，保留样本级不确定性结构，适合可信推理场景。
输出不确定性反映模型输出的概率特性是否具备客观性。与多数机器学习损失函数和指标不同，不确定性关注单个样本，但难以对单一样本进行验证；而集体验证又无法充分体现个体属性，这在小数据集上校准模型置信度时构成挑战。为应对监督学习中分类器输出幅度逐步放大的负面影响，本文提出一种后处理参数化校准方法——ρ-范数校准（ρ-Norm Scaling），该方法拓展了校准表达形式，在抑制因幅度过大导致的过度自信的同时，维持模型精度。此外，基于分箱级别的目标优化常导致重要样本级信息丢失，因此本文引入概率分布正则化项，利用先验知识：校准后的样本级不确定性分布应与校准前相似。实验表明，所提方法在后处理校准中显著提升了不确定性校准性能。
原文摘要 · Abstract (English)
Output uncertainty indicates whether the probabilistic properties reflect objective characteristics of the model output. Unlike most loss functions and metrics in machine learning, uncertainty pertains to individual samples, but validating it on individual samples is unfeasible. When validated collectively, it cannot fully represent individual sample properties, posing a challenge in calibrating model confidence in a limited data set. Hence, it is crucial to consider confidence calibration characteristics. To counter the adverse effects of the gradual amplification of the classifier output amplitude in supervised learning, we introduce a post-processing parametric calibration method, $ρ$-Norm Scaling, which expands the calibrator expression and mitigates overconfidence due to excessive amplitude while preserving accuracy. Moreover, bin-level objective-based calibrator optimization often results in the loss of significant instance-level information. Therefore, we include probability distribution regularization, which incorporates specific priori information that the instance-level uncertainty distribution after calibration should resemble the distribution before calibration. Experimental results demonstrate the substantial enhancement in the post-processing calibrator for uncertainty calibration with our proposed method.
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。