Szczegóły publikacji
Opis bibliograficzny
Unveiling the search space of simple contrastive graph clustering with Cartesian Genetic Programming / Maciej KRZYWDA, Yue Liu, Szymon ŁUKASIK, Amir H. Gandomi // W: GECCO'25 Companion [Dokument elektroniczny] : proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion : July 14–18, 2025, Málaga, Spain. — Wersja do Windows. — Dane tekstowe. — New York : Association for Computing Machinery, 2025. — e-ISBN: 979-8-4007-1464-1. — S. 2380–2383. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 2382, Abstr. — Publikacja dostępna online od: 2025-08-11. — Sz. Łukasik - dod. afiliacje: Systems Research Institute, Polish Academy of Sciences, Warsaw ; NASK National Research Institute, Warsaw
Autorzy (4)
- AGHKrzywda Maciej
- Liu Yue
- AGHŁukasik Szymon
- Gandomi Amir H.
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 161866 |
|---|---|
| Data dodania do BaDAP | 2025-09-03 |
| Tekst źródłowy | URL |
| DOI | 10.1145/3712255.3734538 |
| Rok publikacji | 2025 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Association for Computing Machinery (ACM) |
| Konferencja | Genetic and Evolutionary Computations 2025 |
Abstract
This paper proposes an enhanced approach to Simple Contrastive Graph Clustering (SCGC) by utilizing 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.
