Channel Geometry Preserving Generative Models for CSI Feedback in MU-MIMO

TL;DR

This paper introduces flow-matching generative models for CSI feedback in MU-MIMO, improving channel reconstruction quality and interference suppression over traditional MSE-based methods.

Contribution

It develops novel BS-side flow-matching generative decoders that better preserve channel geometry for MU-MIMO precoding, outperforming MSE-based approaches.

Findings

Flow-based methods outperform MSE baselines in sum-rate.

Proposed methods are especially effective in interference-limited regimes.

Flow reconstruction better preserves channel geometry for user separation.

Abstract

Under limited feedback, channel state information (CSI) reconstruction for multiuser multiple-input multiple-output (MU-MIMO) precoding is challenging, since the precoder should provide not only beamforming gain, but also robust suppression of inter-user interference. This paper revisits this classic problem by developing powerful decompression techniques at the base station (BS) that harness modern deep generative models. We propose two novel BS-side flow-matching generative CSI decoders that progressively transform either a simple prior or an initial CSI estimate into a reconstruction consistent with the feedback-conditioned channel distribution. We further show theoretically that conventional minimum mean-squared-error (MMSE)-based reconstructions of CSI often result in centroid-like compromises that fail to preserve the posterior geometry needed for inter-user interference suppression. In other words, MU-MIMO precoding based on MSE-oriented CSI reconstructions can be suboptimal, since such reconstructions frequently fail to maintain user orthogonality. Numerical results in FR3 spectrum show that the proposed flow-based methods consistently outperform MSE-based baselines in downlink sum-rate, with the advantage especially pronounced in interference-limited and spatially dense regimes. These results suggest that posterior-guided flow reconstruction is better aligned with MU-MIMO precoding than traditional MMSE-oriented CSI feedback, since it better preserves the channel geometry needed for user separation.