Unveiling the Search Space of Simple Contrastive Graph Clustering with Cartesian Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8528

@InProceedings{krzywda:2025:GECCOcomp2,

• author = "Maciej Krzywda and Yue Liu and Szymon Lukasik and Amir H. Gandomi",
• title = "Unveiling the Search Space of Simple Contrastive Graph Clustering with Cartesian Genetic Programming",
• booktitle = "Neuroevolution at work",
• year = "2025",
• editor = "Ernesto Tarantino and De Falco Ivanoe and Antonio {Della Cioppa} and Edgar Galvan and Mengjie Zhang",
• pages = "2380--2383",
• address = "Malaga, Spain",
• series = "GECCO '25 Companion",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, cartesian genetic programming, contrastive graph clustering, evolutionary algorithms, graph neural networks, graph clustering, contrastive learning, Neuroevolution",
• isbn13 = "979-8-4007-1464-1",
• URL = "https://doi.org/10.1145/3712255.3734538",
• DOI = "doi:10.1145/3712255.3734538",
• size = "4 pages",
• abstract = "This paper proposes an enhanced approach to Simple Contrastive Graph Clustering (SCGC) by using Cartesian Genetic Programming (CGP) to evolve neural network architectures. The evolutionary algorithm dynamically optimizes the structure and hyperparameters of SCGC, including the number and size of linear layers, optimizer choice (such as Adam, RMSprop, or SGD), learning rates, weight decay, and loss functions, tailored specifically to the given datasets. Using CGP, we automate both the design and training of SCGC architectures, evolving optimized neural networks with minimal manual intervention. Experimental results conducted across multiple generations on ten benchmark datasets demonstrate that our evolved SCGC consistently achieves superior clustering performance compared to state-of-the-art methods, with notable improvements in accuracy, F1-score, and computational efficiency. The evolutionary process not only optimizes the network topology, but also systematically refines hyperparameters, resulting in robust, highly adaptive, and computationally efficient clustering solutions.",
• notes = "GECCO-2025 NEWK workshop A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Maciej Krzywda Yue Liu Szymon Lukasik A H Gandomi

Citations