Rate split multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond, especially in vehicular scenarios. However, RSMA requires complicated iterative algorithms for proper resource allocation, which cannot fulfill the stringent latency requirement in resource constrained vehicles. Although data driven approaches can alleviate this issue, they suffer from poor generalizability and scarce training data. In this paper, we propose a fractional programming (FP) based deep unfolding (DU) approach to address resource allocation problem for a weighted sum rate optimization in RSMA. By carefully designing the penalty function, we couple the variable update with projected gradient descent algorithm (PGD). Following the structure of PGD, we embed few learnable parameters in each layer of the DU network. Through extensive simulation, we have shown that the proposed model-based neural networks has similar performance as optimal results given by traditional algorithm but with much lower computational complexity, less training data, and higher resilience to test set data and out-of-distribution (OOD) data.

翻译：速率分割多址接入（RSMA）已被证明是5G及未来通信系统（尤其是车载场景）中的有效通信方案。然而，RSMA需要复杂的迭代算法进行资源分配，无法满足资源受限车辆对严格时延的要求。尽管数据驱动方法可缓解该问题，但其泛化能力差且训练数据稀缺。本文提出一种基于分数规划（FP）的深度展开（DU）方法，以解决RSMA中加权和速率优化的资源分配问题。通过精心设计惩罚函数，我们将变量更新与投影梯度下降算法（PGD）耦合。遵循PGD架构，我们在DU网络的每层嵌入少量可学习参数。大量仿真表明，所提出的基于模型的神经网络具有与传统算法给出的最优结果相似的性能，但其计算复杂度显著降低，所需训练数据更少，且对测试集数据和分布外（OOD）数据具有更高的鲁棒性。