Evolving Interpretable Classification Models via Readability-Enhanced Genetic Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.8010
- @InProceedings{De-Souza-Abreu:2022:SSCI,
-
author = "Joao Victor T. {De Souza Abreu} and
Denis Mayr Lima Martins and Fernando Buarque {De Lima Neto}",
-
booktitle = "2022 IEEE Symposium Series on Computational
Intelligence (SSCI)",
-
title = "Evolving Interpretable Classification Models via
Readability-Enhanced Genetic Programming",
-
year = "2022",
-
pages = "1691--1697",
-
abstract = "As the impact of Machine Learning (ML) on business and
society grows, there is a need for making opaque ML
models transparent and interpretable, especially in the
light of fairness, bias, and discrimination.
Nevertheless, interpreting complex opaque models is not
trivial. Current interpretability approaches rely on
local explanations or produce long explanations that
tend to overload the user's cognitive abilities. In
this paper, we address this problem by extracting
interpretable, transparent models from opaque ones via
a new readability-enhanced multi-objective Genetic
Programming approach called REMO-GP. To achieve that,
we adapt text readability metrics into model complexity
proxies that support evaluating ML interpretability. We
demonstrate that our approach can generate global
interpretable models that mimic the decisions of
complex opaque models over several datasets, while
keeping model complexity low.",
-
keywords = "genetic algorithms, genetic programming",
-
DOI = "doi:10.1109/SSCI51031.2022.10022164",
-
month = dec,
-
notes = "Also known as \cite{10022164}",
- }
Genetic Programming entries for
Joao Victor Tinoco De Souza Abreu
Denis Mayr Lima Martins
Fernando Buarque de Lima Neto
Citations