...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Knowledge and information systems >Auditing black-box models for indirect influence
【24h】

Auditing black-box models for indirect influence

机译：审计黑匣子模型，用于间接影响

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior and in particular how different features influence the model prediction. This is important when interpreting the behavior of complex models or asserting that certain problematic attributes (such as race or gender) are not unduly influencing decisions. In this paper, we present a technique for auditing black-box models, which lets us study the extent to which existing models take advantage of particular features in the data set, without knowing how the models work. Our work focuses on the problem of indirect influence: how some features might indirectly influence outcomes via other, related features. As a result, we can find attribute influences even in cases where, upon further direct examination of the model, the attribute is not referred to by the model at all. Our approach does not require the black-box model to be retrained. This is important if, for example, the model is only accessible via an API, and contrasts our work with other methods that investigate feature influence such as feature selection. We present experimental evidence for the effectiveness of our procedure using a variety of publicly available data sets and models. We also validate our procedure using techniques from interpretable learning and feature selection, as well as against other black-box auditing procedures. To further demonstrate the effectiveness of this technique, we use it to audit a black-box recidivism prediction algorithm.
机译：数据训练的预测模型参见广泛使用，但对于大多数情况下，它们用作输出预测或分数的黑匣子。因此，难以获得对模型行为的更深理解，特别是不同的特征如何影响模型预测。这在解释复杂模型的行为或断言某些有问题的属性（如种族或性别）并未过度影响决策时非常重要。在本文中，我们提出了一种用于审计黑盒式模型的技术，这使我们能够研究现有模型在数据集中利用特定功能的程度，而不知道模型如何工作。我们的工作侧重于间接影响问题：某些功能可能会通过其他相关特征间接地影响结果。结果，我们可以在案件中找到属性影响，即使在进一步直接检查模型时，该属性根本不会被模型引用。我们的方法不需要再培训黑匣子模型。例如，如果模型仅通过API访问，则这是重要的，并且对与调查特征影响（例如特征选择）的其他方法对比进行对比。我们使用各种公开的数据集和模型提出了我们程序的有效性的实验证据。我们还使用来自可解释的学习和特征选择的技术以及其他黑匣子审计程序验证我们的程序。为了进一步证明这种技术的有效性，我们将其用来审核黑盒常规预测算法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号