Learning to Code on Graphs for Topological Interference Management
Abstract
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.
Cite
@article{arxiv.2305.07186,
title = {Learning to Code on Graphs for Topological Interference Management},
author = {Zhiwei Shan and Xinping Yi and Han Yu and Chung-Shou Liao and Shi Jin},
journal= {arXiv preprint arXiv:2305.07186},
year = {2023}
}
Comments
An extended version of a paper accepted by International Symposium on Information Theory (ISIT) 2023