Improved representation and genetic operators for linear genetic programming for automated program repair
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{oliveira:2018:ESE,
-
author = "Vinicius Paulo L. Oliveira and
Eduardo {Faria de Souza} and Claire {Le Goues} and
Celso G. Camilo-Junior",
-
title = "Improved representation and genetic operators for
linear genetic programming for automated program
repair",
-
journal = "Empirical Software Engineering",
-
year = "2018",
-
volume = "23",
-
number = "5",
-
pages = "2980--3006",
-
month = oct,
-
note = "Special Issue on Automatic Software Repair",
-
keywords = "genetic algorithms, genetic programming, genetic
improvement, Automatic software repair, Automated
program repair, APR, Crossover operator, Mutation
operator",
-
ISSN = "1382-3256",
-
URL = "https://www.researchgate.net/publication/322704893_Improved_representation_and_genetic_operators_for_linear_genetic_programming_for_automated_program_repair",
-
URL = "http://link.springer.com/article/10.1007/s10664-017-9562-9",
-
DOI = "doi:10.1007/s10664-017-9562-9",
-
size = "27 pages",
-
abstract = "Genetic improvement for program repair can fix bugs or
otherwise improve software via patch evolution.
Consider GenProg, a prototypical technique of this
type. GenProg crossover and mutation operators
manipulate individuals represented as patches. A patch
is composed of high-granularity edits that indivisibly
comprise an edit operation,a faulty location, and a fix
statement used in replacement or insertions. We observe
that recombination and mutation of such high-level
units limits the technique ability to effectively
traverse and recombine the repair search spaces. We
propose a reformulation of program repair
representation, crossover, and mutation operators such
that they explicitly traverse the three sub-spaces that
underlie the search problem: the Operator, Fault and
FixSpaces. We provide experimental evidence validating
our insight, showing that the operators provide
considerable improvement over the baseline repair
algorithm in terms of search success rate and
efficiency. We also conduct a genotypic distance
analysis over the various types of search, providing
insight as to the influence of the operators on the
program repair search problem.",
-
notes = "Instituto de Informatica, Universidade Federal de
Goias (UFG), Goiania, Brazil",
- }
Genetic Programming entries for
Vinicius Paulo Lopes de Oliveira
Eduardo F de Souza
Claire Le Goues
Celso G Camilo-Junior
Citations