Learning with Category-Equivariant Representations for Human Activity Recognition

TL;DR

This paper introduces a category-equivariant learning framework for human activity recognition that enhances model stability and accuracy under various sensor distortions by leveraging symmetry principles in feature representations.

Contribution

It proposes a novel symmetry-aware approach that encodes categorical invariances, improving robustness and out-of-distribution performance in sensor-based activity recognition.

Findings

46 percentage point improvement in out-of-distribution accuracy

3.6x performance gain over baseline models

Enhanced stability under sensor distortions

Abstract

Human activity recognition is challenging because sensor signals shift with context, motion, and environment; effective models must therefore remain stable as the world around them changes. We introduce a categorical symmetry-aware learning framework that captures how signals vary over time, scale, and sensor hierarchy. We build these factors into the structure of feature representations, yielding models that automatically preserve the relationships between sensors and remain stable under realistic distortions such as time shifts, amplitude drift, and device orientation changes. On the UCI Human Activity Recognition benchmark, this categorical symmetry-driven design improves out-of-distribution accuracy by approx. 46 percentage points (approx. 3.6x over the baseline), demonstrating that abstract symmetry principles can translate into concrete performance gains in everyday sensing tasks via category-equivariant representation theory.