Learning to Code on Graphs for Topological Interference Management
Paper in proceeding, 2023

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 via local graph coloring algorithms, leveraging the new advances of graph neural networks (GNNs) and reinforcement learning (RL). 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.

Author

Zhiwei Shan

University of Liverpool

Xinping Yi

University of Liverpool

Han Yu

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Chung Shou Liao

National Tsing Hua University

S. Jin

Southeast University

IEEE International Symposium on Information Theory - Proceedings

21578095 (ISSN)

Vol. 2023-June 2386-2391
9781665475549 (ISBN)

2023 IEEE International Symposium on Information Theory, ISIT 2023
Taipei, Taiwan,

Subject Categories

Computer Science

DOI

10.1109/ISIT54713.2023.10206636

More information

Latest update

10/3/2023