ABSTRACT
Next-generation genetic algorithms (GAs) should explore information from the problem structure whenever possible. Variable interactions can be inferred using linkage learning. Statistical linkage learning techniques were shown to improve GAs' effectiveness significantly in many problems, but may eventually report false linkages. On the other hand, empirical linkage learning (ELL) techniques discover only true variable dependencies. However, traditional ELL techniques are computationally expensive. We introduce the genetic algorithm with linkage learning (GAwLL), which discovers an empirical weighted variable interaction graph (VIGw) as a side-effect of the optimization performed by a GA, making it a no-cost ELL technique. Vertices of the VIGw represent decision variables and weights indicate the strength of the interaction between variables. The VIGw allows us to obtain new insights about the optimization problem and can be used to design genetic operators that efficiently explore the information about variable dependencies. Experiments with NK landscapes show that GAwLL is able to efficiently build the empirical VIGw. We also present an interesting machine learning application, where the VIGw represents a feature interaction network. By using GAwLL, the feature interaction network is built as a side-effect of evolutionary feature selection.
- F. Chicano, G. Ochoa, D. Whitley, and R. Tinós. 2022. Dynastic potential crossover operator. Evolutionary Computation 30, 3 (2022), 409--446.Google ScholarCross Ref
- K. Deb and C. Myburgh. 2016. Breaking the billion-variable barrier in real-world optimization using a customized evolutionary algorithm. In Proc. of GECCO'2016. 653--660.Google Scholar
- D. Dua and C. Graff. 2017. UCI Machine Learning Repository. http://archive.ics.uci.edu/mlGoogle Scholar
- J. H. Friedman and B. E. Popescu. 2008. Predictive learning via rule ensembles. The Annals of Applied Statistics (2008), 916--954.Google Scholar
- B. W. Goldman and W. F. Punch. 2014. Parameter-less Population Pyramid. In Proc. of GECCO'2014. 785--792.Google Scholar
- R. B. Heckendorn. 2002. Embedded Landscapes. Evolutionary Computation 10, 4 (2002), 345--369.Google ScholarDigital Library
- S.-H. Hsu and T.-L. Yu. 2015. Optimization by Pairwise Linkage Detection, Incremental Linkage Set, and Restricted / Back Mixing: DSMGA-II. In Proc. of GECCO'2015. 519--526.Google ScholarDigital Library
- A. Inglis, A. Parnell, and C. B. Hurley. 2022. Visualizing variable importance and variable interaction effects in machine learning models. Journal of Computational and Graphical Statistics (2022), 1--13.Google Scholar
- J. Li, K. Cheng, S. Wang, F. Morstatter, R. P. Trevino, J. Tang, and H. Liu. 2017. Feature selection: A data perspective. ACM Computing Surveys (CSUR) 50, 6 (2017), 1--45.Google ScholarDigital Library
- M. W. Przewozniczek and M. M. Komarnicki. 2020. Empirical Linkage Learning. IEEE Transactions on Evolutionary Computation 24, 6 (2020), 1097--1111.Google ScholarDigital Library
- M. W. Przewozniczek, M. M. Komarnicki, and B. Frej. 2021. Direct linkage discovery with empirical linkage learning. In Proc. of GECCO'2021. 609--617.Google Scholar
- D. Thierens and P. A. N. Bosman. 2012. Predetermined versus Learned Linkage Models. In Proc. of GECCO'2012. 289--296.Google ScholarDigital Library
- D. Thierens and P. A. N. Bosman. 2013. Hierarchical problem solving with the linkage tree genetic algorithm. In Proc. of GECCO'2013. 877--884.Google ScholarDigital Library
- R. Tinós, M. W. Przewozniczek, and D. Whitley. 2022. Iterated local search with perturbation based on variables interaction for pseudo-boolean optimization. In Proc. of GECCO'2022. 296--304.Google Scholar
- R. Tinós, M. W. Przewozniczek, D. Whitley, and F. Chicano. 2023. Iterated Local Search with Linkage Learning. Submitted to ACM TELO (2023).Google Scholar
- R. Tinós, D. Whitley, and F. Chicano. 2015. Partition crossover for pseudo-boolean optimization. In Proceedings of the 2015 ACM Conference on Foundations of Genetic Algorithms XIII. 137--149.Google Scholar
- J. J. M. Van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan, R. G. H. Beets-Tan, J.-C. Fillion-Robin, S. Pieper, and H. J. W. L. Aerts. 2017. Computational radiomics system to decode the radiographic phenotype. Cancer Research 77, 21 (2017), e104--e107.Google ScholarCross Ref
- L. Wang and A. Wong. 2020. COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest radiography images. arXiv preprint arXiv:2003.09871 (2020).Google Scholar
- D. Whitley. 2019. Next generation genetic algorithms: a user's guide and tutorial. In Handbook of Metaheuristics. Springer, 245--274.Google Scholar
- B. Xue, M. Zhang, W. N. Browne, and X. Yao. 2016. A survey on evolutionary computation approaches to feature selection. IEEE Transactions on Evolutionary Computation 20, 4 (2016), 606--626.Google ScholarDigital Library
Index Terms
- Genetic Algorithm with Linkage Learning
Recommendations
Pairwise and problem-specific distance metrics in the linkage tree genetic algorithm
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationThe linkage tree genetic algorithm (LTGA) identifies linkages between problem variables using an agglomerative hierarchical clustering algorithm and linkage trees. This enables LTGA to solve many decomposable problems that are difficult with more ...
Linkage tree genetic algorithm: first results
GECCO '10: Proceedings of the 12th annual conference companion on Genetic and evolutionary computationWe introduce the Linkage Tree Genetic Algorithm (LTGA), a competent genetic algorithm that learns the linkage between the problem variables. The LTGA builds each generation a linkage tree using a hierarchical clustering algorithm. To generate new ...
More concise and robust linkage learning by filtering and combining linkage hierarchies
GECCO '13: Proceedings of the 15th annual conference on Genetic and evolutionary computationGenepool Optimal Mixing Evolutionary Algorithms (GOMEAs) were recently proposed as a new way of designing linkage-friendly, efficiently-scalable evolutionary algorithms (EAs). GOMEAs combine the building of linkage models with an intensive, greedy ...
Comments