<span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction
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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/5/4/76 |
| _version_ | 1797380235580145664 |
|---|---|
| author | Louisa Heidrich Emanuel Slany Stephan Scheele Ute Schmid |
| author_facet | Louisa Heidrich Emanuel Slany Stephan Scheele Ute Schmid |
| author_sort | Louisa Heidrich |
| collection | DOAJ |
| description | 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 <span style="font-variant: small-caps;">Caipi</span> for fair machine learning. <span style="font-variant: small-caps;">FairCaipi</span> incorporates human feedback in the loop on predictions and explanations to improve the fairness of the model. Experimental results demonstrate that <span style="font-variant: small-caps;">FairCaipi</span> 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 <span style="font-variant: small-caps;">FairCaipi</span> can both uncover and reduce bias in machine-learning models and allows us to detect human bias. |
| first_indexed | 2024-03-08T20:34:26Z |
| format | Article |
| id | doaj.art-018e7c40286944bd89ca20b50af98b43 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-08T20:34:26Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-018e7c40286944bd89ca20b50af98b432023-12-22T14:22:10ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902023-10-01541519153810.3390/make5040076<span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias ReductionLouisa Heidrich0Emanuel Slany1Stephan Scheele2Ute Schmid3Cognitive Systems, University of Bamberg, An der Weberei 5, 96047 Bamberg, GermanyCognitive Systems, University of Bamberg, An der Weberei 5, 96047 Bamberg, GermanyCognitive Systems, University of Bamberg, An der Weberei 5, 96047 Bamberg, GermanyCognitive Systems, University of Bamberg, An der Weberei 5, 96047 Bamberg, GermanyThe 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 <span style="font-variant: small-caps;">Caipi</span> for fair machine learning. <span style="font-variant: small-caps;">FairCaipi</span> incorporates human feedback in the loop on predictions and explanations to improve the fairness of the model. Experimental results demonstrate that <span style="font-variant: small-caps;">FairCaipi</span> 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 <span style="font-variant: small-caps;">FairCaipi</span> can both uncover and reduce bias in machine-learning models and allows us to detect human bias.https://www.mdpi.com/2504-4990/5/4/76fair machine learningexplanatory and interactive machine learning |
| spellingShingle | Louisa Heidrich Emanuel Slany Stephan Scheele Ute Schmid <span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction Machine Learning and Knowledge Extraction fair machine learning explanatory and interactive machine learning |
| title | <span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction |
| title_full | <span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction |
| title_fullStr | <span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction |
| title_full_unstemmed | <span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction |
| title_short | <span style="font-variant: small-caps">FairCaipi</span>: A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction |
| title_sort | span style font variant small caps faircaipi span a combination of explanatory interactive and fair machine learning for human and machine bias reduction |
| topic | fair machine learning explanatory and interactive machine learning |
| url | https://www.mdpi.com/2504-4990/5/4/76 |
| work_keys_str_mv | AT louisaheidrich spanstylefontvariantsmallcapsfaircaipispanacombinationofexplanatoryinteractiveandfairmachinelearningforhumanandmachinebiasreduction AT emanuelslany spanstylefontvariantsmallcapsfaircaipispanacombinationofexplanatoryinteractiveandfairmachinelearningforhumanandmachinebiasreduction AT stephanscheele spanstylefontvariantsmallcapsfaircaipispanacombinationofexplanatoryinteractiveandfairmachinelearningforhumanandmachinebiasreduction AT uteschmid spanstylefontvariantsmallcapsfaircaipispanacombinationofexplanatoryinteractiveandfairmachinelearningforhumanandmachinebiasreduction |