A One-Vs-One Approach to Improve Tangled Program Graph Performance on Classification Tasks

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{DBLP:conf/ijcci/BellangerBCH23,

• author = "Thibaut Bellanger and Matthieu {Le Berre} and Manuel Clergue and Jin-Kao Hao",
• title = "A One-Vs-One Approach to Improve Tangled Program Graph Performance on Classification Tasks",
• booktitle = "Proceedings of the 15th International Joint Conference on Computational Intelligence, IJCCI 2023",
• year = "2023",
• editor = "Niki {van Stein} and Francesco Marcelloni and H. K. Lam and Marie Cottrell and Joaquim Filipe",
• address = "Rome, Italy",
• publisher = "SCITEPRESS",
• month = nov # " 13-15",
• pages = "53--63",
• keywords = "genetic algorithms, genetic programming, Classification, Tangled Program Graph, Ensemble Learning, Evolutionary Machine Learning, Evolutionary Search and Meta-Heuristics",
• timestamp = "Fri, 08 Dec 2023 12:42:26 +0100",
• biburl = "https://dblp.org/rec/conf/ijcci/BellangerBCH23.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• URL = "https://www.insticc.org/node/TechnicalProgram/ijcci/2023/presentationDetails/121677",
• DOI = "doi:10.5220/0012167700003595",
• abstract = "We propose an approach to improve the classification performance of the Tangled Programs Graph (TPG). TPG is a genetic programming method that aims to discover Directed Acyclic Graphs (DAGs) through an evolutionary process, where the edges carry programs that allow nodes to create a route from the root to a leaf, and the leaves represent actions or labels in classification. Despite notable successes in reinforcement learning tasks, TPG performance in classification appears to be limited in its basic version, as evidenced by the scores obtained on the MNIST dataset. However, the advantage of TPG compared to neural networks is to obtain, like decision trees, a global decision that is decomposable into simple atomic decisions and thus more easily explainable. Compared to decision trees, TPG has the advantage that atomic decisions benefit from the expressiveness of a pseudo register-based programming language, and the graph evolutionary construction prevents the emergence of overfitting. Our approach consists of decomposing the multi-class problem into a set of one-vs-one binary problems, training a set of TPG for each of them, and then combining the results of the TPGs to obtain a global decision, after selecting the best ones by a genetic algorithm. We test our approach on several benchmark datasets, and the results obtained are promising and tend to validate the proposed method.",
• notes = "ECTA23-RP-32",

}

Genetic Programming entries for Thibaut Bellanger Matthieu Le Berre Manuel Clergue Jin-Kao Hao

Citations