Version 1
: Received: 2 October 2024 / Approved: 2 October 2024 / Online: 3 October 2024 (08:22:07 CEST)
How to cite:
Maldini, A. Review of Meta-heuristics Methods for Machine Learning With Graph Neural Network. Preprints2024, 2024100192. https://doi.org/10.20944/preprints202410.0192.v1
Maldini, A. Review of Meta-heuristics Methods for Machine Learning With Graph Neural Network. Preprints 2024, 2024100192. https://doi.org/10.20944/preprints202410.0192.v1
Maldini, A. Review of Meta-heuristics Methods for Machine Learning With Graph Neural Network. Preprints2024, 2024100192. https://doi.org/10.20944/preprints202410.0192.v1
APA Style
Maldini, A. (2024). Review of Meta-heuristics Methods for Machine Learning With Graph Neural Network. Preprints. https://doi.org/10.20944/preprints202410.0192.v1
Chicago/Turabian Style
Maldini, A. 2024 "Review of Meta-heuristics Methods for Machine Learning With Graph Neural Network" Preprints. https://doi.org/10.20944/preprints202410.0192.v1
Abstract
In this paper, we review metaheuristic optimization techniques for machine learning with Graph Neural Networks (GNNs), focusing on two major categories: single-solution-based and population-based metaheuristics. We provide an in-depth analysis of Genetic Algorithms (GA) and Particle Swarm Optimization (PSO), highlighting their effectiveness in optimizing GNN hyperparameters. By exploring the strengths and weaknesses of these methods, we aim to provide insights into their application and performance in enhancing the efficiency and accuracy of GNN models. We will also review the similarities of supervised learning and metaheuristic solutions.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
