Self-Supervised and Invariant Representations for Wireless Localization

TL;DR

This paper introduces a self-supervised wireless localization method that learns robust, transferable channel representations without labeled data, outperforming supervised techniques especially in small data scenarios across diverse environments.

Contribution

It presents the first joint-embedding self-supervised approach for wireless localization that does not rely on contrastive channel estimates, enhancing transferability and robustness.

Findings

Outperforms supervised methods in small data regimes.

Effective in both indoor and outdoor environments.

Works across centralized and distributed MIMO systems.

Abstract

In this work, we present a wireless localization method that operates on self-supervised and unlabeled channel estimates. Our self-supervising method learns general-purpose channel features robust to fading and system impairments. Learned representations are easily transferable to new environments and ready to use for other wireless downstream tasks. To the best of our knowledge, the proposed method is the first joint-embedding self-supervised approach to forsake the dependency on contrastive channel estimates. Our approach outperforms fully-supervised techniques in small data regimes under fine-tuning and, in some cases, linear evaluation. We assess the performance in centralized and distributed massive MIMO systems for multiple datasets. Moreover, our method works indoors and outdoors without additional assumptions or design changes.