Joint Sensing, Communication, and Computation for Vertical Federated Edge Learning in Edge Perception Network

TL;DR

This paper introduces a vertical federated edge learning framework that integrates sensing, communication, and computation to improve data fusion and model training in edge perception networks, addressing limitations of traditional horizontal federated learning.

Contribution

The paper proposes a novel VFEEL framework that effectively combines wireless sensing and over-the-air computation for feature-partitioned data in edge networks.

Findings

Analyzes convergence behavior under sensing noise and aggregation distortions.

Demonstrates improved data fusion in multiview edge sensing scenarios.

Provides theoretical insights into loss function degradation.

Abstract

Combining wireless sensing and edge intelligence, edge perception networks enable intelligent data collection and processing at the network edge. However, traditional sample partition based horizontal federated edge learning struggles to effectively fuse complementary multiview information from distributed devices. To address this limitation, we propose a vertical federated edge learning (VFEEL) framework tailored for feature-partitioned sensing data. In this paper, we consider an integrated sensing, communication, and computation-enabled edge perception network, where multiple edge devices utilize wireless signals to sense environmental information for updating their local models, and the edge server aggregates feature embeddings via over-the-air computation for global model training. First, we analyze the convergence behavior of the ISCC-enabled VFEEL in terms of the loss function degradation in the presence of wireless sensing noise and aggregation distortions during AirComp.