BENN: Bias Estimation Using a Deep Neural Network

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

Research output: Contribution to journalArticlepeer-review

Abstract

Utilizing existing methods for bias detection in machine learning (ML) models is challenging since each method: 1) explores a different ethical aspect of bias, which may result in contradictory output among the different methods; 2) provides output in a different range/scale and therefore cannot be compared with other methods; and 3) requires different input, thereby requiring a human expert's involvement to adjust each method according to the model examined. In this article, we present BENN, a novel bias estimation method that uses a pretrained unsupervised deep neural network. Given an ML model and data samples, BENN provides a bias estimation for every feature based on the examined model's predictions. We evaluated BENN using three benchmark datasets, one proprietary churn prediction model used by a European telecommunications company, and a synthetic dataset that includes both a biased feature and a fair one. BENN's results were compared with an ensemble of 21 existing bias estimation methods. The evaluation results show that BENN provides bias estimations that are aligned with those of the ensemble while offering significant advantages, including the fact that it is a generic approach (i.e., can be applied to any ML model) and does not require a domain expert.

Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
StateAccepted/In press - 1 Jan 2022

Keywords

  • Bias estimation
  • Data models
  • deep neural network (DNN)
  • Ethical aspects
  • Ethics
  • ethics
  • fairness estimation
  • Feature extraction
  • machine learning (ML)
  • Maximum likelihood estimation
  • Neural networks
  • Predictive models
  • unsupervised learning.

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'BENN: Bias Estimation Using a Deep Neural Network'. Together they form a unique fingerprint.

Cite this