Graph-based deep learning for communication networks: A survey

Communication networks are important infrastructures in contemporary society. There still many challenges that not fully solved and new solutions proposed continuously this active research area. In recent years, to model the network topology, graph-based deep learning has achieved state-of-the-art performance a series of problems communication networks. survey, we review rapidly growing body using different models, e.g. graph convolutional attention networks, various from types wireless wired software defined We also present well-organized list problem solution for each study identify future directions. To best our knowledge, paper is first survey focuses on application methods involving both scenarios. track follow-up research, public GitHub repository created, where relevant papers will be updated continuously.