Channel Extrapolation for MIMO Systems with the Assistance of Multi-path Information Induced from Channel State Information

TL;DR

This work tackles the overhead of obtaining full CSI in 6G by introducing environment-aware channel extrapolation that relies on PDP-derived multi-path information extracted directly from CSI. A CSI-to-PDP AE recovers PDPs from CSI, producing concise multi-path cues such as total power and power-weighted delay, which are fused with a dual-branch MAE using cross-attention to extrapolate the complete channel. The approach demonstrates up to approximately 4–5 dB improvements in extrapolation accuracy with minimal inference-time impact and shows strong cross-frequency generalization, particularly when only a small fraction of CSI is available. The method reduces reliance on additional sensors while leveraging environment-related propagation features to enhance extrapolation reliability and efficiency.

Abstract

Acquiring channel state information (CSI) through traditional methods, such as channel estimation, is increasingly challenging for the emerging sixth generation (6G) mobile networks due to high overhead. To address this issue, channel extrapolation techniques have been proposed to acquire complete CSI from a limited number of known CSIs. To improve extrapolation accuracy, environmental information, such as visual images or radar data, has been utilized, which poses challenges including additional hardware, privacy and multi-modal alignment concerns. To this end, this paper proposes a novel channel extrapolation framework by leveraging environment-related multi-path characteristics induced directly from CSI without integrating additional modalities. Specifically, we propose utilizing the multi-path characteristics in the form of power-delay profile (PDP), which is acquired using a CSI-to-PDP module. CSI-to-PDP module is trained in an AE-based framework by reconstructing the PDPs and constraining the latent low-dimensional features to represent the CSI. We further extract the total power & power-weighted delay of all the identified paths in PDP as the multi-path information. Building on this, we proposed a MAE architecture trained in a self-supervised manner to perform channel extrapolation. Unlike standard MAE approaches, our method employs separate encoders to extract features from the masked CSI and the multi-path information, which are then fused by a cross-attention module. Extensive simulations demonstrate that this framework improves extrapolation performance dramatically, with a minor increase in inference time (around 0.1 ms). Furthermore, our model shows strong generalization capabilities, particularly when only a small portion of the CSI is known, outperforming existing benchmarks.

Figures (10)

• Figure 1: Overal architecture of the proposed model, which consists of a CSI-to-PDP and channel extrapolation modules. The CSI-to-PDP module infers PDP using CSI via a CSI-to-PDP decoder, which is training in a auto-encoder (AE) manner illustrated in Fig. \ref{['fig:CSI-to-PDP']}. The channel extrapolation module is developed based on a masked auto-encoder (MAE), where the features of masked CSI and PDP indicators are extracted separately using dedicated encoders and fused subsequently. The fused features are finally utilized to reconstruct the complete CSI using a decoder.
• Figure 2: Training procedure of the CSI-to-PDP in an auto-encoder (AE) manner. To enable the mapping between CSI and PDP, the output of the CSI-to-PDP encoder is forced to be CSI by using the summation of reconstruction error of CSI and PDP.
• Figure 3: Fusion of the multi-path information and CSI features.
• Figure 4: Simulation scenario.
• Figure 5: Illustration of the training and testing loss.

Theorems & Definitions (1)

• Definition 1