Synesthesia of Machines (SoM)-Aided FDD Precoding with Sensing Heterogeneity: A Vertical Federated Learning Approach

TL;DR

This paper presents a novel vertical federated learning-based precoding scheme for frequency division duplex systems that reduces pilot sequence length and adapts dynamically to user fluctuations, improving efficiency and performance.

Contribution

Introduces a heterogeneous multi-modal sensing aided precoding scheme within a VFL framework, addressing data heterogeneity and enabling dynamic adaptation in FDD systems.

Findings

Significantly reduces pilot sequence length while maintaining high sum rate.

Achieves performance close to traditional methods with perfect channel information.

Demonstrates effective handling of data heterogeneity and user fluctuations.

Abstract

High complexity in precoding design for frequency division duplex systems necessitates streamlined solutions. Guided by Synesthesia of Machines (SoM), this paper introduces a heterogeneous multi-vehicle, multi-modal sensing aided precoding scheme within a vertical federated learning (VFL) framework, which significantly minimizes pilot sequence length while optimizing the system's sum rate. We address the challenges posed by local data heterogeneity due to varying on-board sensor configurations through a meticulously designed VFL training procedure. To extract valuable channel features from multi-modal sensing, we employ three distinct data preprocessing methods that convert raw data into informative representations relevant for precoding. Additionally, we propose an online training strategy based on VFL framework, enabling the scheme to adapt dynamically to fluctuations in user numbers. Numerical results indicate that our approach, utilizing short pilot sequences, closely approximates the performance of traditional optimization methods with perfect channel state information.