The field of graph neural networks is rapidly advancing, with a growing focus on dynamic systems and temporal dependencies. Recent research has explored the application of graph neural networks to various domains, including air traffic control, social networks, and urban mobility. A key direction in this field is the development of efficient and effective models that can capture complex temporal and spatial dependencies. Notable progress has been made in improving the scalability and interpretability of graph neural networks, enabling their application to real-world problems such as demand prediction, route optimization, and sustainability. Some noteworthy papers in this area include: The paper Air Traffic Controller Task Demand via Graph Neural Networks, which introduces an interpretable Graph Neural Network framework to predict air traffic controller task demand. The paper When Speed meets Accuracy, which proposes a lightweight framework called EAGLE for temporal link prediction in dynamic graphs, achieving superior performance and efficiency compared to state-of-the-art models.