No abstract

With the rapid enhancement of computer computing power, deep learning methods, e.g., convolution neural networks, recurrent neural networks, etc., have been applied in wireless network widely and achieved impressive performance. In recent years, in order to mine the topology information of graphstructured data in wireless network as well as contextual information, graph neural networks have been introduced and have achieved the state-of-the-art performance of a series of wireless network problems. In this review, we first simply introduce the progress of several classical paradigms, such as graph convolutional neural networks, graph attention networks, graph autoencoder, graph recurrent networks, graph reinforcement learning and spatial-temporal graph neural networks, of graph neural networks comprehensively. Then, several applications of graph neural networks in wireless networks such as power control, link scheduling, channel control, wireless traffic prediction, vehicular communication, point cloud, etc., are discussed in detail. Finally, some research trends about the applications of graph neural networks in wireless networks are discussed.

In wireless network, the optimization problems generally have complex constraints, and are usually solved via utilizing the traditional optimization methods that have high computational complexity and need to be executed repeatedly with the change of network environments. In this paper, to overcome these shortcomings, an unsupervised deep unrolling framework based on projection gradient descent, i.e., unrolled PGD network (UPGDNet), is designed to solve a family of constrained optimization problems. The set of constraints is divided into two categories according to the coupling relations among optimization variables and the convexity of constraints. One category of constraints includes convex constraints with decoupling among optimization variables, and the other category of constraints includes non-convex or convex constraints with coupling among optimization variables. Then, the first category of constraints is directly projected onto the feasible region, while the second category of constraints is projected onto the feasible region using neural network. Finally, an unrolled sum rate maximization network (USRMNet) is designed based on UPGDNet to solve the weighted SR maximization problem for the multiuser ultra-reliable low latency communication system. Numerical results show that USRMNet has a comparable performance with low computational complexity and an acceptable generalization ability in terms of the user distribution.

No abstract

No abstract