Using graph neural networks as surrogate models in genetic programming
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F22%3A00561586" target="_blank" >RIV/67985807:_____/22:00561586 - isvavai.cz</a>
Alternative codes found
RIV/00216208:11320/22:10455086
Result on the web
<a href="https://dx.doi.org/10.1145/3520304.3529024" target="_blank" >https://dx.doi.org/10.1145/3520304.3529024</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/3520304.3529024" target="_blank" >10.1145/3520304.3529024</a>
Alternative languages
Result language
angličtina
Original language name
Using graph neural networks as surrogate models in genetic programming
Original language description
Surrogate models have been used for decades to speed up evolutionary algorithms, however, most of their uses are tailored for problems with simple individual encoding, like vectors of numbers. In this paper, we evaluate the possibility to use two different types of graph neural networks to predict the quality of a solution in tree-based genetic programming without evaluating the trees. The proposed models are evaluated in a number of benchmarks from symbolic regression and reinforcement learning and show that GNNs can be successfully used as surrogate models for problems with a complex structure.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
GECCO 2022 Companion - Proceedings of the 2022 Genetic and Evolutionary Computation Conference
ISBN
978-1-4503-9268-6
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
582-585
Publisher name
ACM
Place of publication
New York
Event location
Boston
Event date
Jul 9, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—