GRLinQ: An Intelligent Spectrum Sharing Mechanism for Device-to-Device Communications with Graph Reinforcement Learning

Device-to-device (D2D) spectrum sharing in wireless communications is a challenging non-convex combinatorial optimization problem, involving entangled link scheduling and power control in a large-scale network. The state-of-the-art methods, either from a model-based or a data-driven perspective, exhibit certain limitations such as the critical need for channel state information (CSI) and/or a large number of (solved) instances (e.g., network layouts) as training samples. To advance this line of research, we propose a novel hybrid model/datadriven spectrum sharing mechanism with graph reinforcement learning for link scheduling (GRLinQ), injecting information theoretical insights into machine learning models, in such a way that link scheduling and power control can be solved in an intelligent yet explainable manner. Through an extensive set of experiments, GRLinQ demonstrates superior performance to the existing model-based and data-driven link scheduling and/or power control methods, with a relaxed requirement for CSI, a substantially reduced number of unsolved instances as training samples, a possible distributed deployment, reduced online/offline computational complexity, and more remarkably excellent scalability and generalizability over different network scenarios and system configurations.

Online TSP with Predictions

We initiate the study of online routing problems with predictions, inspired by recent exciting results in the area of learning-augmented algorithms. A learning-augmented online algorithm which incorporates predictions in a black-box manner to outperform existing algorithms if the predictions are accurate while otherwise maintaining theoretical guarantees even when the predictions are extremely erroneous is a popular framework for overcoming pessimistic worst-case competitive analysis. In this study, we particularly begin investigating the classical online traveling salesman problem (OLTSP), where future requests are augmented with predictions. Unlike the prediction models in other previous studies, each actual request in the OLTSP, associated with its arrival time and position, may not coincide with the predicted ones, which, as imagined, leads to a troublesome situation. Our main result is to study different prediction models and design algorithms to improve the best-known results in the different settings. Moreover, we generalize the proposed results to the online dial-a-ride problem.