Wireless Channel Foundation Model with Embedded Noise-Plus-Interference Suppression Structure

2025-09-19

AI Summary

Existing Wireless Channel Foundation Models (WCFMs) are trained on noiseless, perfect CSI obtained via simulation, whereas real-world systems only acquire degraded CSI—corrupted by estimation noise and interference due to sparse pilot-based channel estimation—leading to representation distortion and significant performance degradation in downstream tasks. Method: We propose the first robust WCFM architecture explicitly designed for degraded CSI modeling. It introduces an embedded joint noise-and-interference suppression module that employs a learnable projection matrix to separate interference components, coupled with a CSI completion network for channel purification and reconstruction; all components are optimized end-to-end. Contribution/Results: Experiments on channel prediction demonstrate substantial gains over state-of-the-art methods. Our approach effectively mitigates performance deterioration caused by imperfect channel estimation in practical deployments and, for the first time, enables unified modeling and suppression of the coupled noise–interference degradation process.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Wireless channel foundation model (WCFM) is a task-agnostic AI model that is pretrained on large-scale wireless channel datasets to learn a universal channel feature representation that can be used for a wide range of downstream tasks related to communications and sensing. While existing works on WCFM have demonstrated its great potentials in various tasks including beam prediction, channel prediction, localization, etc, the models are all trained using perfect (i.e., error-free and complete) channel information state (CSI) data which are generated with simulation tools. However, in practical systems where the WCFM is deployed, perfect CSI is not available. Instead, channel estimation needs to be first performed based on pilot signals over a subset of the resource elements (REs) to acquire a noisy version of the CSI (termed as degraded CSI), which significantly differs from the perfect CSI in some real-world environments with severe noise and interference. As a result, the feature representation generated by the WCFM is unable to reflect the characteristics of the true channel, yielding performance degradation in downstream tasks. To address this issue, in this paper we propose an enhanced wireless channel foundation model architecture with noise-plus-interference (NPI) suppression capability. In our approach, coarse estimates of the CSIs are first obtained. With these information, two projection matrices are computed to extract the NPI terms in the received signals, which are further processed by a NPI estimation and subtraction module. Finally, the resultant signal is passed through a CSI completion network to get a clean version of the CSI, which is used for feature extraction. Simulation results demonstrated that compared to the state-of-the-art solutions, WCFM with NPI suppression structure achieves improved performance on channel prediction task.

Problem

• Addresses performance gap from noisy CSI in wireless models
• Proposes embedded noise-plus-interference suppression in WCFM
• Enhances channel feature representation for downstream tasks

Innovation

• Enhanced WCFM architecture with NPI suppression
• Projection matrices extract noise-plus-interference terms
• CSI completion network produces clean channel representation