Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning

Machine learning methods are growing in relevance for biometrics and personal information processing in domains such as forensics, e-health, recruitment, and e-learning. In these domains, white-box (human-readable) explanations of systems built on machine learning methods become crucial. Inductive l...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alfonso Ortega, Julian Fierrez, Aythami Morales, Zilong Wang, Marina de la Cruz, César Luis Alonso, Tony Ribeiro
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	explainable artificial intelligence inductive logic programming fair recruitment fair income level propositional logic Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/77e40effadd648ebb011d1dd19b2ed88
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:77e40effadd648ebb011d1dd19b2ed88
record_format	dspace
spelling	oai:doaj.org-article:77e40effadd648ebb011d1dd19b2ed882021-11-25T17:17:31ZSymbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning10.3390/computers101101542073-431Xhttps://doaj.org/article/77e40effadd648ebb011d1dd19b2ed882021-11-01T00:00:00Zhttps://www.mdpi.com/2073-431X/10/11/154https://doaj.org/toc/2073-431XMachine learning methods are growing in relevance for biometrics and personal information processing in domains such as forensics, e-health, recruitment, and e-learning. In these domains, white-box (human-readable) explanations of systems built on machine learning methods become crucial. Inductive logic programming (ILP) is a subfield of symbolic AI aimed to automatically learn declarative theories about the processing of data. Learning from interpretation transition (LFIT) is an ILP technique that can learn a propositional logic theory equivalent to a given black-box system (under certain conditions). The present work takes a first step to a general methodology to incorporate accurate declarative explanations to classic machine learning by checking the viability of LFIT in a specific AI application scenario: fair recruitment based on an automatic tool generated with machine learning methods for ranking Curricula Vitae that incorporates soft biometric information (gender and ethnicity). We show the expressiveness of LFIT for this specific problem and propose a scheme that can be applicable to other domains. In order to check the ability to cope with other domains no matter the machine learning paradigm used, we have done a preliminary test of the expressiveness of LFIT, feeding it with a real dataset about adult incomes taken from the US census, in which we consider the income level as a function of the rest of attributes to verify if LFIT can provide logical theory to support and explain to what extent higher incomes are biased by gender and ethnicity.Alfonso OrtegaJulian FierrezAythami MoralesZilong WangMarina de la CruzCésar Luis AlonsoTony RibeiroMDPI AGarticleexplainable artificial intelligenceinductive logic programmingfair recruitmentfair income levelpropositional logicElectronic computers. Computer scienceQA75.5-76.95ENComputers, Vol 10, Iss 154, p 154 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	explainable artificial intelligence inductive logic programming fair recruitment fair income level propositional logic Electronic computers. Computer science QA75.5-76.95
spellingShingle	explainable artificial intelligence inductive logic programming fair recruitment fair income level propositional logic Electronic computers. Computer science QA75.5-76.95 Alfonso Ortega Julian Fierrez Aythami Morales Zilong Wang Marina de la Cruz César Luis Alonso Tony Ribeiro Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning
description	Machine learning methods are growing in relevance for biometrics and personal information processing in domains such as forensics, e-health, recruitment, and e-learning. In these domains, white-box (human-readable) explanations of systems built on machine learning methods become crucial. Inductive logic programming (ILP) is a subfield of symbolic AI aimed to automatically learn declarative theories about the processing of data. Learning from interpretation transition (LFIT) is an ILP technique that can learn a propositional logic theory equivalent to a given black-box system (under certain conditions). The present work takes a first step to a general methodology to incorporate accurate declarative explanations to classic machine learning by checking the viability of LFIT in a specific AI application scenario: fair recruitment based on an automatic tool generated with machine learning methods for ranking Curricula Vitae that incorporates soft biometric information (gender and ethnicity). We show the expressiveness of LFIT for this specific problem and propose a scheme that can be applicable to other domains. In order to check the ability to cope with other domains no matter the machine learning paradigm used, we have done a preliminary test of the expressiveness of LFIT, feeding it with a real dataset about adult incomes taken from the US census, in which we consider the income level as a function of the rest of attributes to verify if LFIT can provide logical theory to support and explain to what extent higher incomes are biased by gender and ethnicity.
format	article
author	Alfonso Ortega Julian Fierrez Aythami Morales Zilong Wang Marina de la Cruz César Luis Alonso Tony Ribeiro
author_facet	Alfonso Ortega Julian Fierrez Aythami Morales Zilong Wang Marina de la Cruz César Luis Alonso Tony Ribeiro
author_sort	Alfonso Ortega
title	Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning
title_short	Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning
title_full	Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning
title_fullStr	Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning
title_full_unstemmed	Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning
title_sort	symbolic ai for xai: evaluating lfit inductive programming for explaining biases in machine learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/77e40effadd648ebb011d1dd19b2ed88
work_keys_str_mv	AT alfonsoortega symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning AT julianfierrez symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning AT aythamimorales symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning AT zilongwang symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning AT marinadelacruz symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning AT cesarluisalonso symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning AT tonyribeiro symbolicaiforxaievaluatinglfitinductiveprogrammingforexplainingbiasesinmachinelearning
_version_	1718412538415153152

Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Explaining Biases in Machine Learning

Ejemplares similares