Graph Neural Networks for Next-Generation-IoT: Recent Advances and Open Challenges

Graph Neural Networks (GNNs) have emerged as a powerful framework for modeling complex interconnected systems, hence making them particularly well-suited to address the growing challenges of next-generation Internet of Things (NG-IoT) networks. Despite increasing interest in this area, existing studies remain fragmented, and there is a lack of comprehensive guidance on how GNNs can be systematically applied to NG-IoT systems. As NG-IoT systems evolve toward 6G, they incorporate diverse technologies such as massive MIMO, reconfigurable intelligent surfaces (RIS), terahertz (THz) communication, satellite systems, mobile edge computing (MEC), and ultra-reliable low-latency communication (URLLC). These advances promise unprecedented connectivity, sensing, and automation but also introduce significant complexity, requiring new approaches for scalable learning, dynamic optimization, and secure, decentralized decision-making. This survey provides a comprehensive and forward-looking exploration of how GNNs can empower NG-IoT environments structured as ten open research questions that span the relevant theoretical foundations, practical deployments, and emerging integration pathways. We commence by exploring the fundamental paradigms of GNNs and articulating the motivation for their use in NG-IoT networks. Besides, to further justify their suitability, we intrinsically connect GNNs for the first time with the family of low-density parity-check (LDPC) codes, modeling the NG-IoT as dynamic constrainted graphs where GNNs harness belief propagation for convergence and interpretability through density evolution and EXIT charts. We highlight the distinct roles of node-, edge-, and graph-level tasks in tackling key challenges and demonstrate the GNNs’ ability to overcome the limitations of traditional optimization methods. Following this, we examine the application of GNNs across core NG-enabling technologies and their integration with distributed frameworks to support privacy preservation and distributed intelligence. We then delve into the challenges posed by adversarial attacks, offering insights into defense mechanisms to secure GNN-based NG-IoT networks. Lastly, we examine how GNNs can be integrated with emerging technologies like integrated sensing and communication (ISAC), satellite-air-ground-sea integrated networks (SAGSIN), and quantum computing. Our findings highlight the transformative potential of GNNs in improving efficiency, scalability, and security within NG-IoT systems, paving the way for future advances. Finally, we summarize the key lessons learned throughout the paper and outline promising future research directions, along with a set of design guidelines aimed at facilitating the development of efficient, scalable, and secure GNN models tailored for NG-IoT applications.