Successive Interference Cancellation-aided Diffusion Models for Joint Channel Estimation and Data Detection in Low Rank Channel Scenarios

TL;DR

This work addresses joint channel estimation and data detection in low-rank uplink channels where the user count $N_u$ exceeds the AP antenna count $N_r$. It introduces a SIC-aided score-based diffusion model that partitions the channel into partial submatrices $H^{(i)}$ and uses a diffusion prior gradient $s_\theta(H^{(i)}, \sigma_{i,H})$ within a MAP framework to iteratively refine both channels and data. A channel-gain-based SIC decoding order is dynamically updated, and partial data symbols $X^{(i)}$ are estimated concurrently. Across extensive simulations on 3GPP/QuaDRiGa channels, the proposed method achieves superior NMSE and SER over baselines in both full-rank and low-rank settings, with the largest improvements in low-rank scenarios, highlighting its practical potential for next-generation uplink systems.

Abstract

This paper proposes a novel joint channel-estimation and source-detection algorithm using successive interference cancellation (SIC)-aided generative score-based diffusion models. Prior work in this area focuses on massive MIMO scenarios, which are typically characterized by full-rank channels, and fail in low-rank channel scenarios. The proposed algorithm outperforms existing methods in joint source-channel estimation, especially in low-rank scenarios where the number of users exceeds the number of antennas at the access point (AP). The proposed score-based iterative diffusion process estimates the gradient of the prior distribution on partial channels, and recursively updates the estimated channel parts as well as the source. Extensive simulation results show that the proposed method outperforms the baseline methods in terms of normalized mean squared error (NMSE) and symbol error rate (SER) in both full-rank and low-rank channel scenarios, while having a more dominant effect in the latter, at various signal-to-noise ratios (SNR).

Figures (4)

• Figure 1: NMSE for high rank
• Figure 2: NMSE for low rank
• Figure 3: SER for high rank
• Figure 4: SER for low rank