arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.05467cs.LGcs.AI
收藏

理解机器学习分类器中的预测差异

Understanding Prediction Discrepancies in Machine Learning Classifiers

AXA(安盛集团);Sorbonne University(索邦大学);CNRS(法国国家科学研究中心);Polish Academy of Science(波兰科学院)

Xavier Renard, Thibault Laugel, Marcin Detyniecki

AI总结:

本文针对同数据上性能相近但分类模式不同的模型选择问题,提出模型无关算法DIG来局部捕获和解释预测差异,帮助实践者预见潜在不良后果并做出更明智的模型选择。

摘要:

大量分类器可以在相同数据上训练,在测试阶段取得相似的性能,但它们学习到的分类模式却存在显著差异。我们将这一现象称为预测差异,它通常与盲目选择一个模型而非另一个性能相近的模型有关。在做出选择时,机器学习实践者并不了解模型之间的差异、它们的局限、它们在哪些地方一致以及哪些地方不一致。但其选择将对处于差异区域中的待分类实例产生具体后果,因为最终决策将基于所选定的分类模式。除了结果的任意性之外,错误的选择还可能带来进一步的负面后果,例如机会丧失或公平性缺失。本文提出通过分析在同一数据上训练的一组最佳性能模型中的预测差异来解决这一问题。我们提出了一种模型无关的算法DIG,用于局部捕获并解释差异,使实践者能够在选择模型时预见其潜在的不良后果,从而做出最明智的决策。所有用于复现实验的代码均已公开。

英文摘要:

A multitude of classifiers can be trained on the same data to achieve similar performances during test time, while having learned significantly different classification patterns. This phenomenon, which we call prediction discrepancies, is often associated with the blind selection of one model instead of another with similar performances. When making a choice, the machine learning practitioner has no understanding on the differences between models, their limits, where they agree and where they don't. But his/her choice will result in concrete consequences for instances to be classified in the discrepancy zone, since the final decision will be based on the selected classification pattern. Besides the arbitrary nature of the result, a bad choice could have further negative consequences such as loss of opportunity or lack of fairness. This paper proposes to address this question by analyzing the prediction discrepancies in a pool of best-performing models trained on the same data. A model-agnostic algorithm, DIG, is proposed to capture and explain discrepancies locally, to enable the practitioner to make the best educated decision when selecting a model by anticipating its potential undesired consequences. All the code to reproduce the experiments is available.

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。

↑