FairCaipi: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction

Author:

Heidrich Louisa1,Slany Emanuel12ORCID,Scheele Stephan12ORCID,Schmid Ute12ORCID

Affiliation:

1. Cognitive Systems, University of Bamberg, An der Weberei 5, 96047 Bamberg, Germany

2. Fraunhofer Institute for Integrated Circuits IIS, Sensory Perception & Analytics, Comprehensible AI, Am Wolfsmantel 33, 91058 Erlangen, Germany

Abstract

The rise of machine-learning applications in domains with critical end-user impact has led to a growing concern about the fairness of learned models, with the goal of avoiding biases that negatively impact specific demographic groups. Most existing bias-mitigation strategies adapt the importance of data instances during pre-processing. Since fairness is a contextual concept, we advocate for an interactive machine-learning approach that enables users to provide iterative feedback for model adaptation. Specifically, we propose to adapt the explanatory interactive machine-learning approach Caipi for fair machine learning. FairCaipi incorporates human feedback in the loop on predictions and explanations to improve the fairness of the model. Experimental results demonstrate that FairCaipi outperforms a state-of-the-art pre-processing bias mitigation strategy in terms of the fairness and the predictive performance of the resulting machine-learning model. We show that FairCaipi can both uncover and reduce bias in machine-learning models and allows us to detect human bias.

Funder

German Ministry of Education and Research

Bavarian Ministry of Economy, Development, and Industry, Germany

Publisher

MDPI AG

Subject

Artificial Intelligence,Engineering (miscellaneous)

Reference50 articles.

1. Martin, K. (2022). Ethics and Data Analytics, Auerbach Publications. Chapter 6.11.

2. Why we should have seen that coming: Comments on Microsoft’s tay “experiment,” and wider implications;Wolf;SIGCAS Comput. Soc.,2017

3. Examining perceptions towards hiring algorithms;Zhang;Technol. Soc.,2022

4. Multi–objective Evolutionary Algorithms for the Risk–return Trade–off in Bank Loan Management;Mukerjee;Int. Trans. Oper. Res.,2002

5. McIlraith, S.A., and Weinberger, K.Q. (2018, January 2–7). Non-Discriminatory Machine Learning Through Convex Fairness Criteria. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, LA, USA.

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Hybrid Explanatory Interactive Machine Learning for Medical Diagnosis;IFIP Advances in Information and Communication Technology;2024

2. Explainable AI for Mixed Data Clustering;Communications in Computer and Information Science;2024

3. Explanatory Interactive Machine Learning with Counterexamples from Constrained Large Language Models;Lecture Notes in Computer Science;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3