arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.07186cs.ITmath.IT
收藏

学习在图上进行编码以实现拓扑干扰管理

Learning to Code on Graphs for Topological Interference Management

Zhiwei Shan, Xinping Yi, Han Yu, Chung-Shou Liao, Shi Jin

AI总结:

本文提出基于图神经网络和强化学习的智能编码框架LCG,通过局部图着色模拟拓扑干扰对齐,实现高泛化性和可迁移性的新编码方案。

摘要:

针对拓扑干扰管理(TIM)问题的最先进编码方案通常是为特定网络拓扑族手工设计的,严重依赖专家的领域知识。这不可避免地限制了其在无线通信系统中更广泛应用的潜力,因为泛化能力有限。本文首次尝试提出一种新颖的智能编码方法,利用图神经网络(GNNs)和强化学习(RL)的最新进展,通过局部图着色算法来模拟拓扑干扰对齐(IA)。所提出的LCG框架随后被推广以发现新的IA编码方案,包括一对一向量IA和子空间IA。大量实验证明了所提方法出色的泛化性和可迁移性,其中由小规模TIM实例训练的参量化GNNs能够很好地适用于具有更大规模的新的未见网络拓扑。

英文摘要:

The state-of-the-art coding schemes for topological interference management (TIM) problems are usually handcrafted for specific families of network topologies, relying critically on experts' domain knowledge. This inevitably restricts the potential wider applications to wireless communication systems, due to the limited generalizability. This work makes the first attempt to advocate a novel intelligent coding approach to mimic topological interference alignment (IA) via local graph coloring algorithms, leveraging the new advances of graph neural networks (GNNs) and reinforcement learning (RL). The proposed LCG framework is then generalized to discover new IA coding schemes, including one-to-one vector IA and subspace IA. The extensive experiments demonstrate the excellent generalizability and transferability of the proposed approach, where the parameterized GNNs trained by small size TIM instances are able to work well on new unseen network topologies with larger size.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑