Using system context information to complement weakly labeled data

TL;DR

This paper introduces a method that leverages system context information through an information graph and contrastive learning to improve accuracy, robustness, and transferability of classifiers trained on weakly labeled sensor data.

Contribution

It presents a novel approach combining system context and contrastive learning to enhance weakly supervised sensor data analysis.

Findings

Improved accuracy with weakly labeled data

Enhanced robustness to sensor environment variations

Better transferability to new sensor locations

Abstract

Real-world datasets collected with sensor networks often contain incomplete and uncertain labels as well as artefacts arising from the system environment. Complete and reliable labeling is often infeasible for large-scale and long-term sensor network deployments due to the labor and time overhead, limited availability of experts and missing ground truth. In addition, if the machine learning method used for analysis is sensitive to certain features of a deployment, labeling and learning needs to be repeated for every new deployment. To address these challenges, we propose to make use of system context information formalized in an information graph and embed it in the learning process via contrastive learning. Based on real-world data we show that this approach leads to an increased accuracy in case of weakly labeled data and leads to an increased robustness and transferability of the classifier to new sensor locations.