A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]

Bibliographic Details
Main Author: Rebuli, Karina Brotto
Publication Date: 2023
Other Authors: Giacobini, Mario, Silva, Sara, Vanneschi, Leonardo
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/156121
Summary: Rebuli, K. B., Giacobini, M., Silva, S., & Vanneschi, L. (2023). A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]. In S. Silva, & L. Paquete (Eds.), GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (pp. 539–542). Association for Computing Machinery (ACM). https://doi.org/10.1145/3583133.3590595 --- This work was partially supported by FCT, Portugal, through funding of research units MagIC/NOVA IMS (UIDB/04152/2020) and LASIGE (UIDB/00408/2020 and UIDP/00408/2020).
id RCAP_3a7fc30133a3cc4c7bb7415f24b4f23c
oai_identifier_str oai:run.unl.pt:10362/156121
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]explainable AIinterpretable modelscomplexity metricsSoftwareComputational Theory and MathematicsComputer Science ApplicationsRebuli, K. B., Giacobini, M., Silva, S., & Vanneschi, L. (2023). A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]. In S. Silva, & L. Paquete (Eds.), GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (pp. 539–542). Association for Computing Machinery (ACM). https://doi.org/10.1145/3583133.3590595 --- This work was partially supported by FCT, Portugal, through funding of research units MagIC/NOVA IMS (UIDB/04152/2020) and LASIGE (UIDB/00408/2020 and UIDP/00408/2020).Genetic Programming (GP) has the potential to generate intrinsically explainable models. Despite that, in practice, this potential is not fully achieved because the solutions usually grow too much during the evolution. The excessive growth together with the functional and structural complexity of the solutions increase the computational cost and the risk of overfitting. Thus, many approaches have been developed to prevent the solutions to grow excessively in GP. However, it is still an open question how these approaches can be used for improving the interpretability of the models. This article presents an empirical study of eight structural complexity metrics that have been used as evaluation criteria in multi-objective optimisation. Tree depth, size, visitation length, number of unique features, a proxy for human interpretability, number of operators, number of non-linear operators and number of consecutive nonlinear operators were tested. The results show that potentially the best approach for generating good interpretable GP models is to use the combination of more than one structural complexity metric.ACM - Association for Computing MachineryInformation Management Research Center (MagIC) - NOVA Information Management SchoolNOVA Information Management School (NOVA IMS)RUNRebuli, Karina BrottoGiacobini, MarioSilva, SaraVanneschi, Leonardo2023-08-01T22:13:38Z2023-07-242023-07-24T00:00:00Zconference objectinfo:eu-repo/semantics/publishedVersion4application/pdfhttp://hdl.handle.net/10362/156121eng979-8-4007-0120-7PURE: 67865636https://doi.org/10.1145/3583133.3590595info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:13:33Zoai:run.unl.pt:10362/156121Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:44:00.949869Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
title A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
spellingShingle A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
Rebuli, Karina Brotto
explainable AI
interpretable models
complexity metrics
Software
Computational Theory and Mathematics
Computer Science Applications
title_short A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
title_full A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
title_fullStr A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
title_full_unstemmed A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
title_sort A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]
author Rebuli, Karina Brotto
author_facet Rebuli, Karina Brotto
Giacobini, Mario
Silva, Sara
Vanneschi, Leonardo
author_role author
author2 Giacobini, Mario
Silva, Sara
Vanneschi, Leonardo
author2_role author
author
author
dc.contributor.none.fl_str_mv Information Management Research Center (MagIC) - NOVA Information Management School
NOVA Information Management School (NOVA IMS)
RUN
dc.contributor.author.fl_str_mv Rebuli, Karina Brotto
Giacobini, Mario
Silva, Sara
Vanneschi, Leonardo
dc.subject.por.fl_str_mv explainable AI
interpretable models
complexity metrics
Software
Computational Theory and Mathematics
Computer Science Applications
topic explainable AI
interpretable models
complexity metrics
Software
Computational Theory and Mathematics
Computer Science Applications
description Rebuli, K. B., Giacobini, M., Silva, S., & Vanneschi, L. (2023). A Comparison of Structural Complexity Metrics for Explainable Genetic Programming [Poster]. In S. Silva, & L. Paquete (Eds.), GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (pp. 539–542). Association for Computing Machinery (ACM). https://doi.org/10.1145/3583133.3590595 --- This work was partially supported by FCT, Portugal, through funding of research units MagIC/NOVA IMS (UIDB/04152/2020) and LASIGE (UIDB/00408/2020 and UIDP/00408/2020).
publishDate 2023
dc.date.none.fl_str_mv 2023-08-01T22:13:38Z
2023-07-24
2023-07-24T00:00:00Z
dc.type.driver.fl_str_mv conference object
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/156121
url http://hdl.handle.net/10362/156121
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 979-8-4007-0120-7
PURE: 67865636
https://doi.org/10.1145/3583133.3590595
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 4
application/pdf
dc.publisher.none.fl_str_mv ACM - Association for Computing Machinery
publisher.none.fl_str_mv ACM - Association for Computing Machinery
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596924731588608

Similar Items