Association-Aware GNN for Precoder Learning in Cell-Free Systems

TL;DR

This paper introduces an association-aware graph neural network for precoder learning in cell-free systems, effectively incorporating user-AP association dynamics to improve performance and generalization in multi-user MIMO scenarios.

Contribution

The paper proposes a novel AAGNN that explicitly models UE-AP associations, leveraging permutation equivariance and attention mechanisms for efficient and generalizable precoder learning.

Findings

AAGNN outperforms baseline methods in learning accuracy.

AAGNN demonstrates superior generalization to different association scenarios.

The approach maintains low training and inference complexity.

Abstract

Deep learning has been widely recognized as a promising approach for optimizing multi-user multi-antenna precoders in traditional cellular systems. However, a critical distinction between cell-free and cellular systems lies in the flexibility of user equipment (UE)-access point (AP) associations. Consequently, the optimal precoder depends not only on channel state information but also on the dynamic UE-AP association status. In this paper, we propose an association-aware graph neural network (AAGNN) that explicitly incorporates association status into the precoding design. We leverage the permutation equivariance properties of the cell-free precoding policy to reduce the training complexity of AAGNN and employ an attention mechanism to enhance its generalization performance. Simulation results demonstrate that the proposed AAGNN outperforms baseline learning methods in both learning performance and generalization capabilities while maintaining low training and inference complexity.