Distributionally Robust Semi-Supervised Learning for People-Centric Sensing

TL;DR

This paper introduces a distributionally robust semi-supervised learning model tailored for people-centric sensing, effectively handling distribution shifts caused by diverse human biological and behavioral variations.

Contribution

It presents a novel model that reduces person-specific discrepancies and maintains task-specific consistency, improving semi-supervised learning under distributional shifts in people-centric data.

Findings

Outperforms state-of-the-art methods across multiple recognition tasks

Effective in handling distribution shifts in real-world datasets

Enhances semi-supervised learning accuracy for human-centric sensing

Abstract

Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, human-generated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biological conditions and behavior patterns of humans. To address this problem, we propose a generic distributionally robust model for semi-supervised learning on distributionally shifted data. Considering both the discrepancy and the consistency between the labeled data and the unlabeled data, we learn the latent features that reduce person-specific discrepancy and preserve task-specific consistency. We evaluate our model in a variety of people-centric recognition tasks on real-world datasets, including intention recognition, activity recognition, muscular movement recognition and gesture recognition. The experiment results demonstrate that the proposed model outperforms the state-of-the-art methods.