AINeutralarXiv – CS AI · 14h ago6/10
🧠
Evolutionary Refinement of Generative Graph Topologies: A Hybrid WGAN-GA Approach
Researchers have developed a hybrid approach combining Wasserstein GANs with Genetic Algorithms to improve synthetic graph generation by refining structural properties like degree and spectral distributions. The method reduces deviations from real-world graphs while preserving diversity, advancing generative models for realistic graph synthesis and data augmentation applications.