arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2401.08348cs.LG
收藏

无标签条件下协变量偏移中的模型性能估计

Estimating Model Performance Under Covariate Shift Without Labels

NannyML NV Belgium(NannyML比利时公司);University of Helsinki(赫尔辛基大学)

Jakub Białek, Juhani Kivimäki, Wojtek Kuberski, Nikolaos Perrakis

AI总结:

本文提出 PAPE,仅利用模型预测与概率估计,在无标签表格数据上无需假设协变量偏移性质即可估计二分类性能,并在 900 多种组合中验证其优于基准方法。

摘要:

部署之后,机器学习模型常因数据分布变化而出现性能下降。当标签缺失或延迟时,准确评估部署后的性能颇具挑战。现有代理方法(如数据漂移检测)无法充分衡量这些变化带来的影响。为解决该问题,我们提出一种在无标签表格数据上评估二分类模型的新方法,可准确估计协变量偏移下的模型性能,并将其命名为 Probabilistic Adaptive Performance Estimation(PAPE,概率自适应性能估计)。该方法适用于任何由混淆矩阵元素定义的性能指标。关键在于,PAPE 独立于原始模型运行,仅依赖模型预测和概率估计,且不需要对协变量偏移的性质作任何假设,而是直接从数据中学习。我们使用来自美国人口普查数据的 900 多种数据集-模型组合测试了 PAPE,并通过多种指标将其性能与若干基准进行比较。结果表明,PAPE 优于其他方法,因此是估计二分类模型性能的更优选择。

英文摘要:

After deployment, machine learning models often experience performance degradation due to shifts in data distribution. It is challenging to assess post-deployment performance accurately when labels are missing or delayed. Existing proxy methods, such as data drift detection, fail to measure the effects of these shifts adequately. To address this, we introduce a new method for evaluating binary classification models on unlabeled tabular data that accurately estimates model performance under covariate shift and call it Probabilistic Adaptive Performance Estimation (PAPE). It can be applied to any performance metric defined with elements of the confusion matrix. Crucially, PAPE operates independently of the original model, relying only on its predictions and probability estimates, and does not need any assumptions about the nature of covariate shift, learning directly from data instead. We tested PAPE using over 900 dataset-model combinations from US census data, assessing its performance against several benchmarks through various metrics. Our findings show that PAPE outperforms other methodologies, making it a superior choice for estimating the performance of binary classification models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑