A Unified Two-Stage Generative Diffusion Framework for Channel Estimation and Port Selection in Multiuser MIMO-FAS

2026-05-28

AI Summary

This work addresses the coupled challenges of channel state information acquisition and combinatorial port selection in multi-user MIMO systems with fluid antennas. To tackle this, the paper proposes the first unified two-stage diffusion framework that formulates the joint task as a maximum a posteriori inference problem, decomposing it into sequential stages of continuous channel estimation and discrete port selection. The approach uniquely integrates a flow-based continuous diffusion model—enabling high-fidelity channel recovery through parallel guided generation—with a discrete diffusion model that combines supervised learning and reinforcement fine-tuning to achieve globally optimal port selection. Under extremely low sampling ratios, the proposed method substantially improves the system’s minimum achievable rate, overcoming the susceptibility of conventional heuristic algorithms to suboptimal local solutions.

Abstract

Fluid antenna systems (FAS) have emerged as a promising technology for next-generation wireless systems. However, practical multiuser multiple-input multiple-output FAS (MIMO-FAS) faces two inherently coupled challenges: acquiring accurate high-dimensional channel state information (CSI) from limited RF chains and solving the combinatorial port selection problem, where the effectiveness of the latter highly depends on the result of the former. In this paper, we propose a unified two-stage diffusion framework that formulates the joint task as a maximum-a-posteriori (MAP) inference problem and decomposes it into two sequential sampling stages through a plug-in approximation. For Stage I, a continuous flow-based diffusion model serves as a powerful implicit prior for 2D FAS channels, and a parallel guided generation scheme realizes approximate posterior sampling, enabling accurate multiuser channel recovery even under severely low sub-sampling ratios. For Stage II, a discrete diffusion model is trained to approximate the conditional port selection distribution by combining supervised learning on heuristic labels with reinforcement fine-tuning, effectively overcoming the local optima of conventional heuristic algorithms. Extensive simulations demonstrate that the proposed framework simultaneously achieves exceptional channel estimation accuracy and globally optimized port selection, substantially improving the minimum achievable rate.

Problem

• channel estimation
• port selection
• MIMO-FAS
• fluid antenna systems
• combinatorial optimization

Innovation

• diffusion model
• channel estimation
• port selection
• MIMO-FAS
• maximum-a-posteriori inference