What's inside the black-box?: a genetic programming method for interpreting complex machine learning models

Created by W.Langdon from gp-bibliography.bib Revision:1.8129

@InProceedings{Evans:2019:GECCO,

• author = "Benjamin P. Evans and Bing Xue and Mengjie Zhang",
• title = "What's inside the black-box?: a genetic programming method for interpreting complex machine learning models",
• 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 = "1012--1020",
• address = "Prague, Czech Republic",
• DOI = "doi:10.1145/3321707.3321726",
• publisher = "ACM",
• publisher_address = "New York, NY, USA",
• month = "13-17 " # jul,
• organisation = "SIGEVO",
• keywords = "genetic algorithms, genetic programming, Explainable Artificial Intelligence, Interpretable Machine Learning, Evolutionary Multi-objective Optimisation",
• size = "9 pages",
• abstract = "Interpreting state-of-the-art machine learning algorithms can be difficult. For example, why does a complex ensemble predict a particular class? Existing approaches to interpretable machine learning tend to be either local in their explanations, apply only to a particular algorithm, or overly complex in their global explanations. In this work, we propose a global model extraction method which uses multi-objective genetic programming to construct accurate, simplistic and model-agnostic representations of complex black-box estimators. We found the resulting representations are far simpler than existing approaches while providing comparable reconstructive performance. This is demonstrated on a range of datasets, by approximating the knowledge of complex black-box models such as 200 layer neural networks and ensembles of 500 trees, with a single tree.",
• notes = "Also known as \cite{3321726} 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 Benjamin Evans Bing Xue Mengjie Zhang

Citations