SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing

TL;DR

SPAR is a self-supervised learning framework that explicitly models sensor placement and signal relationships to improve robustness and generalization in distributed sensing applications.

Contribution

It introduces a novel placement-aware representation learning method using dual reconstruction objectives guided by the placement-signal duality.

Findings

Achieves superior robustness across modalities and placements

Outperforms placement-agnostic methods in generalization

Supported by information-theoretic and occlusion-invariant analyses

Abstract

We present SPAR, a framework for self-supervised placement-aware representation learning in distributed sensing. Distributed sensing spans applications where multiple spatially distributed and multimodal sensors jointly observe an environment, from vehicle monitoring to human activity recognition and earthquake localization. A central challenge shared by this wide spectrum of applications is that observed signals are inseparably shaped by sensor placements, including their spatial locations and structural characteristics. However, existing pretraining methods remain largely placement-agnostic. SPAR addresses this gap through a unifying principle: the duality between signals and positions. Guided by this principle, SPAR introduces spatial and structural positional embeddings together with dual reconstruction objectives, explicitly modeling how observing positions and observed signals shape each other. Placement is thus treated not as auxiliary metadata but as intrinsic to representation learning. SPAR is theoretically supported by analyses from information theory and occlusion-invariant learning. Extensive experiments on three real-world datasets show that SPAR achieves superior robustness and generalization across various modalities, placements, and downstream tasks.