Why Train-and-Select When You Can Use Them All?: Ensemble Model for Fault Localisation

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Sohn:2019:GECCO,

• author = "Jeongju Sohn and Shin Yoo",
• title = "Why Train-and-Select When You Can Use Them All?: Ensemble Model for Fault Localisation",
• booktitle = "GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference",
• year = "2019",
• editor = "Manuel Lopez-Ibanez and Thomas Stuetzle and Anne Auger and Petr Posik and Leslie {Peprez Caceres} and Andrew M. Sutton and Nadarajen Veerapen and Christine Solnon and Andries Engelbrecht and Stephane Doncieux and Sebastian Risi and Penousal Machado and Vanessa Volz and Christian Blum and Francisco Chicano and Bing Xue and Jean-Baptiste Mouret and Arnaud Liefooghe and Jonathan Fieldsend and Jose Antonio Lozano and Dirk Arnold and Gabriela Ochoa and Tian-Li Yu and Holger Hoos and Yaochu Jin and Ting Hu and Miguel Nicolau and Robin Purshouse and Thomas Baeck and Justyna Petke and Giuliano Antoniol and Johannes Lengler and Per Kristian Lehre",
• isbn13 = "978-1-4503-6111-8",
• pages = "1408--1416",
• address = "Prague, Czech Republic",
• DOI = "doi:10.1145/3321707.3321873",
• publisher = "ACM",
• publisher_address = "New York, NY, USA",
• month = "13-17 " # jul,
• organisation = "SIGEVO",
• keywords = "genetic algorithms, genetic programming, SBSE, Search-based software engineering, Fault Localisation, Fitness Evaluation, Defects4J",
• size = "9 pages",
• abstract = "Learn-to-rank techniques have been successfully applied to fault localisation to produce ranking models that place faulty program elements at or near the top. Genetic Programming has been successfully used as a learning mechanism to produce highly effective ranking models for fault localisation. However, the inherent stochastic nature of GP forces its users to learn multiple ranking models and choose the best performing one for the actual use. This train-and-select approach means that the absolute majority of the computational resources that go into the evolution of ranking models are eventually wasted. We introduce Ensemble Model for Fault Localisation (EMF), which is a learn-to-rank fault localisation technique that uses all trained models to improve the accuracy of localisation even further. EMF ranks program elements using a lightweight, voting-based ensemble of ranking models. We evaluate EMF using 389 real-world faults in Defects4J benchmark. EMF can place 30.1percent more faults at the top when compared to the best performing individual model from the train-and-select approach. We also apply Genetic Algorithm (GA) to construct the best performing ensemble. Compared to naively using all ranking models, GA generated ensembles can localise further 9.2percent more faults at the top on average.",
• notes = "Also known as \cite{3321873} GECCO-2019 A Recombination of the 28th International Conference on Genetic Algorithms (ICGA) and the 24th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Jeongju Sohn Shin Yoo

Citations