ABSTRACT
Graph representations promise several desirable properties for Genetic Programming (GP); multiple-output programs, natural representations of code reuse and, in many cases, an innate mechanism for neutral drift. Each graph GP technique provides a program representation, genetic operators and overarching evolutionary algorithm. This makes it difficult to identify the individual causes of empirical differences, both between these methods and in comparison to traditional GP. In this work, we empirically study the behavior of Cartesian Genetic Programming (CGP), Linear Genetic Programming (LGP), Evolving Graphs by Graph Programming (EGGP) and traditional GP. By fixing some aspects of the configurations, we study the performance of each graph GP method and GP in combination with three different EAs: generational, steady-state and (1 + λ). In general, we find that the best choice of representation, genetic operator and evolutionary algorithm depends on the problem domain. Further, we find that graph GP methods, particularly in combination with the (1 + λ) EA are significantly better on digital circuit synthesis tasks.
- Timothy Atkinson, Detlef Plump, and Susan Stepney. 2018. Evolving Graphs by Graph Programming. In European Conference on Genetic Programming. Springer International Publishing, Cham, 35--51.Google ScholarCross Ref
- Timothy Atkinson, Detlef Plump, and Susan Stepney. 2018. Probabilistic Graph Programs for Randomised and Evolutionary Algorithms. In Proc. International Conference on Graph Transformation, ICGT 2018 (LNCS), Vol. 10887. Springer, 63--78.Google ScholarDigital Library
- Timothy Atkinson, Detlef Plump, and Susan Stepney. 2019. Evolving Graphs with Semantic Neutral Drift. Natural Computing (2019). https://arxiv.org/abs/1810.10453Google Scholar
- Timothy Atkinson, Detlef Plump, and Susan Stepney. 2020. Horizontal gene transfer for recombining graphs. Genetic Programming and Evolvable Machines (2020).Google Scholar
- M. Brameier and W. Banzhaf. 2001. Effective Linear Genetic Programming. Technical Report. Department of Computer Science, University of Dortmund, 44221 Dortmund, Germany.Google Scholar
- M. F. Brameier and W. Banzhaf. 2007. Linear genetic programming. Springer.Google Scholar
- Andrea Corradini, Ugo Montanari, Francesca Rossi, Hartmut Ehrig, Reiko Heckel, and Michael Löwe. 1997. Algebraic approaches to graph transformation-part i: Basic concepts and double pushout approach. In Handbook Of Graph Grammars And Computing By Graph Transformation: Volume 1: Foundations. World Scientific, 163--245.Google Scholar
- Christopher Fogelberg and Mengjie Zhang. 2005. Linear Genetic Programming for Multi-class Object Classification. In AI 2005: Advances in Artificial Intelligence. Springer Berlin Heidelberg, Berlin, Heidelberg, 369--379.Google Scholar
- Félix-Antoine Fortin, François-Michel De Rainville, Marc-André Gardner, Marc Parizeau, and Christian Gagné. 2012. DEAP: Evolutionary Algorithms Made Easy. Journal of Machine Learning Research 13 (jul 2012), 2171--2175.Google ScholarDigital Library
- Sean Harris, Travis Bueter, and Daniel R. Tauritz. 2015. A Comparison of Genetic Programming Variants for Hyper-Heuristics. In GECCO 2015 5th Workshop on Evolutionary Computation for the Automated Design of Algorithms (ECADA'15). Madrid, Spain, 1043--1050.Google Scholar
- Paul Kaufmann and Marco Platzner. 2018. Combining Local and Global Search: A Multi-objective Evolutionary Algorithm for Cartesian Genetic Programming. 175--194. Google ScholarCross Ref
- J. R. Koza. 1991. Evolving a Computer Program to Generate Random Numbers Using the Genetic Programming Paradigm. In Proc. Intl. Conf. on Genetic Algorithms. Morgan Kaufmann, 37--44.Google Scholar
- John R. Koza. 1992. Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge, MA, USA.Google ScholarDigital Library
- James McDermott, David R. White, Sean Luke, Luca Manzoni, Mauro Castelli, Leonardo Vanneschi, Wojciech Jaskowski, Krzysztof Krawiec, Robin Harper, Kenneth De Jong, and Una-May O'Reilly. 2012. Genetic Programming Needs Better Benchmarks. In Proceedings of the 14th Annual Conference on Genetic and Evolutionary Computation (GECCO '12). 791--798.Google ScholarDigital Library
- Julian Miller. 2019. Cartesian genetic programming: its status and future. Genetic Programming and Evolvable Machines (08 2019). Google ScholarCross Ref
- Julian F. Miller. 1999. An empirical study of the efficiency of learning boolean functions using a Cartesian Genetic Programming approach. In Proceedings of the Genetic and Evolutionary Computation Conference, Vol. 2. Morgan Kaufmann, Orlando, Florida, USA, 1135--1142.Google Scholar
- J. F. Miller and S. L. Smith. 2006. Redundancy and computational efficiency in Cartesian genetic programming. IEEE Transactions on Evolutionary Computation 10, 2 (April 2006), 167--174. Google ScholarDigital Library
- Julian F. Miller and Peter Thomson. 2000. Cartesian Genetic Programming. In Genetic Programming, Riccardo Poli, Wolfgang Banzhaf, William B. Langdon, Julian Miller, Peter Nordin, and Terence C. Fogarty (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 121--132.Google ScholarDigital Library
- Riccardo Poli, William B. Langdon, and Nicholas Freitag McPhee. 2008. A field guide to genetic programming. Published via http://lulu.com and freely available at http://www.gp-field-guide.org.uk. (With contributions by J. R. Koza).Google Scholar
- Leo Francoso Dal Piccol Sotto, Vinicius Veloso de Melo, and Marcio Porto Basgalupp. 2017. λ-LGP: an improved version of linear genetic programming evaluated in the Ant Trail problem. Knowledge and Information Systems 52, 2 (Aug. 2017), 445--465.Google Scholar
- Léo Françoso Dal Piccol Sotto and Franz Rothlauf. 2019. On the Role of Non-effective Code in Linear Genetic Programming. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '19). ACM, New York, NY, USA, 1075--1083.Google ScholarDigital Library
- Andrew James Turner and Julian Francis Miller. 2015. Neutral genetic drift: an investigation using Cartesian Genetic Programming. Genetic Programming and Evolvable Machines 16, 4 (Dec 2015), 531--558. Google ScholarDigital Library
- András Vargha and Harold D. Delaney. 2000. A Critique and Improvement of the CL Common Language Effect Size Statistics of McGraw and Wong. Journal of Educational and Behavioral Statistics 25, 2 (2000), 101--132.Google Scholar
- Vesselin K. Vassilev and Julian F. Miller. 2000. The Advantages of Landscape Neutrality in Digital Circuit Evolution. In Evolvable Systems: From Biology to Hardware, Julian Miller, Adrian Thompson, Peter Thomson, and Terence C. Fogarty (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 252--263.Google ScholarDigital Library
- James Alfred Walker. 2007. The Automatic Acquisition, Evolution and Reuse of Modules in Cartesian Genetic Programming. IEEE Transactions on Evolutionary Computation 12 (2007), 397--417.Google ScholarDigital Library
- Garnett Wilson and Wolfgang Banzhaf. 2008. A Comparison of Cartesian Genetic Programming and Linear Genetic Programming. In Genetic Programming, Michael O'Neill, Leonardo Vanneschi, Steven Gustafson, Anna Isabel Esparcia Alcázar, Ivanoe De Falco, Antonio Della Cioppa, and Ernesto Tarantino (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 182--193.Google ScholarDigital Library
- Tina Yu and Julian F. Miller. 2001. Neutrality and the Evolvability of Boolean Function Landscape. In Proceedings of the 4th European Conference on Genetic Programming (EuroGP '01). Springer-Verlag, Berlin, Heidelberg, 204--217. http://dl.acm.org/citation.cfm?id=646809.704083Google ScholarDigital Library
Index Terms
- A study on graph representations for genetic programming
Recommendations
Graph-based linear genetic programming: a case study of dynamic scheduling
GECCO '22: Proceedings of the Genetic and Evolutionary Computation ConferenceLinear genetic programming (LGP) has been successfully applied to various problems such as classification, symbolic regression and hyper-heuristics for automatic heuristic design. In contrast with the traditional tree-based genetic programming (TGP), ...
Graph representations in genetic programming
AbstractGraph representations promise several desirable properties for genetic programming (GP); multiple-output programs, natural representations of code reuse and, in many cases, an innate mechanism for neutral drift. Each graph GP technique provides a ...
A comparison of Cartesian genetic programming and linear genetic programming
EuroGP'08: Proceedings of the 11th European conference on Genetic programmingTwo prominent genetic programming approaches are the graph-based Cartesian Genetic Programming (CGP) and Linear Genetic Programming (LGP). Recently, a formal algorithm for constructing a directed acyclic graph (DAG) from a classical LGP instruction ...
Comments