arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.12537cs.LGcs.CY
收藏

BENN:使用深度神经网络进行偏差估计

BENN: Bias Estimation Using Deep Neural Network

Ben-Gurion University of the Negev(内盖夫本-古里安大学);Technische Universitat Berlin(柏林工业大学);Deutsche Telekom AG(德国电信股份公司)

Amit Giloni, Edita Grolman, Tanja Hagemann, Ronald Fromm, Sebastian Fischer, Yuval Elovici, Asaf Shabtai

摘要:

在机器学习(ML)模型中检测偏差的需求导致了多种偏差检测方法的发展,但利用它们是具有挑战性的,因为每种方法:i)探索偏见的不同伦理方面,这可能导致不同方法之间的矛盾输出,ii)提供不同范围/尺度的输出,因此不能与其他方法进行比较,以及iii)需要不同的输入,因此需要人类专家参与以根据所检查的模型来调整每种方法。在本文中,我们提出了BENN --一种使用预训练的无监督深度神经网络的新型偏差估计方法。给定ML模型和数据样本,BENN根据模型的预测为每个特征提供偏差估计。我们使用三个基准数据集和一个欧洲电信公司使用的专有流失预测模型评估了BENN,并将其与21种现有偏差估计方法的集合进行了比较。评估结果突出了BENN相对于集合的显著优势,因为它是通用的(即,可以应用于任何ML模型),并且不需要领域专家,但它提供了与集合一致的偏差估计。

英文摘要:

The need to detect bias in machine learning (ML) models has led to the development of multiple bias detection methods, yet utilizing them is challenging since each method: i) explores a different ethical aspect of bias, which may result in contradictory output among the different methods, ii) provides an output of a different range/scale and therefore, can't be compared with other methods, and iii) requires different input, and therefore a human expert needs to be involved to adjust each method according to the examined model. In this paper, we present BENN -- a novel bias estimation method that uses a pretrained unsupervised deep neural network. Given a ML model and data samples, BENN provides a bias estimation for every feature based on the model's predictions. We evaluated BENN using three benchmark datasets and one proprietary churn prediction model used by a European Telco and compared it with an ensemble of 21 existing bias estimation methods. Evaluation results highlight the significant advantages of BENN over the ensemble, as it is generic (i.e., can be applied to any ML model) and there is no need for a domain expert, yet it provides bias estimations that are aligned with those of the ensemble.

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。

↑