In this paper, we delve into the challenge of optimizing joint communication and computation for semantic communication over wireless networks using a probability graph framework. In the considered model, the base station (BS) extracts the small-sized compressed semantic information through removing redundant messages based on the stored knowledge base. Specifically, the knowledge base is encapsulated in a probability graph that encapsulates statistical relations. At the user side, the compressed information is accurately deduced using the same probability graph employed by the BS. While this approach introduces an additional computational overhead for semantic information extraction, it significantly curtails communication resource consumption by transmitting concise data. We derive both communication and computation cost models based on the inference process of the probability graph. Building upon these models, we introduce a joint communication and computation resource allocation problem aimed at minimizing the overall energy consumption of the network, while accounting for latency, power, and semantic constraints. To address this problem, we obtain a closed-form solution for transmission power under a fixed semantic compression ratio. Subsequently, we propose an efficient linear search-based algorithm to attain the optimal solution for the considered problem with low computational complexity. Simulation results underscore the effectiveness of our proposed system, showcasing notable improvements compared to conventional non-semantic schemes.

翻译：本文深入探讨了在概率图框架下，针对无线网络上的语义通信，优化联合通信与计算的挑战。在所考虑的模型中，基站（BS）通过基于存储的知识库移除冗余信息，提取出小尺寸的压缩语义信息。具体而言，知识库被封装在蕴含统计关系的概率图中。在用户端，使用与BS相同的概率图，可以准确推导出压缩信息。虽然这种方法为语义信息提取引入了额外的计算开销，但通过传输简洁数据，显著削减了通信资源消耗。我们基于概率图的推理过程，推导出通信和计算成本模型。基于这些模型，我们提出一个联合通信与计算资源分配问题，旨在最小化网络的总能耗，同时考虑时延、功率和语义约束。为解决该问题，我们在固定语义压缩比下获得了传输功率的闭式解。随后，我们提出一种高效的线性搜索算法，以低计算复杂度获得所考虑问题的最优解。仿真结果凸显了我们所提出系统的有效性，与传统的非语义方案相比，展示了显著的改进。