Multi-Station WiFi CSI Sensing Framework Robust to Station-wise Feature Missingness and Limited Labeled Data

TL;DR

This paper introduces a WiFi CSI sensing framework that effectively handles station-wise feature missingness and limited labeled data by combining self-supervised learning and data augmentation techniques, improving robustness in real-world multi-station deployments.

Contribution

It adapts cross-modal self-supervised learning for CSI data and proposes station-wise masking augmentation to jointly address feature missingness and label scarcity.

Findings

Representation learning becomes invariant to station missingness.

Station-wise Masking Augmentation improves robustness under limited labels.

Combined approach outperforms individual techniques in real-world tests.

Abstract

We propose a WiFi Channel State Information (CSI) sensing framework for multi-station deployments that addresses two fundamental challenges in practical CSI sensing: station-wise feature missingness and limited labeled data. Feature missingness is commonly handled by resampling unevenly spaced CSI measurements or by reconstructing missing samples, while label scarcity is mitigated by data augmentation or self-supervised representation learning. However, these techniques are typically developed in isolation and do not jointly address long-term, structured station unavailability together with label scarcity. To bridge this gap, we explicitly incorporate station unavailability into both representation learning and downstream model training. Specifically, we adapt cross-modal self-supervised learning (CroSSL), a representation learning framework originally designed for time-series sensory data, to multi-station CSI sensing in order to learn representations that are inherently invariant to station-wise feature missingness from unlabeled data. Furthermore, we introduce Station-wise Masking Augmentation (SMA) during downstream model training, which exposes the model to realistic station unavailability patterns under limited labeled data. Our experiments show that neither missingness-invariant pre-training nor station-wise augmentation alone is sufficient; their combination is essential to achieve robust performance under both station-wise feature missingness and label scarcity. The proposed framework provides a practical and robust foundation for multi-station WiFi CSI sensing in real-world deployments.