AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Distributionally Robust Semi-Supervised Learning for People-Centric Sensing

Kaixuan Chen, Lina Yao, Dalin Zhang, Xiaojun Chang, Guodong Long, Sen Wang

AAAI 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the full distributionally robust semi-supervised model instead of the strongest listed baselinePeople-centric sensing recognition · EEGaccuracy: 73.29$\pm$0.68 -> 77.01$\pm$0.89Improved
Use the full distributionally robust semi-supervised model instead of the strongest listed baselinePeople-centric sensing recognition · MHEALTHaccuracy: 92.08$\pm$0.53 -> 95.22$\pm$1.32Improved
Use the full distributionally robust semi-supervised model instead of the strongest listed baselinePeople-centric sensing recognition · EMGaccuracy: 74.46$\pm$0.81 -> 77.83$\pm$0.56Improved
Use the full distributionally robust semi-supervised model instead of the strongest listed baselinePeople-centric sensing recognition · OPPORTUNITYaccuracy: 59.23$\pm$1.72 -> 62.27$\pm$0.54Improved
Add adversarial alignment of labeled and unlabeled feature distributions (ablation)Prediction-loss-only model · EEGaccuracy: 66.62$\pm$0.83 -> 70.79$\pm$0.81Improved
Add adversarial alignment of labeled and unlabeled feature distributions (ablation)Prediction-loss-only model · EMGaccuracy: 64.56$\pm$1.15 -> 69.55$\pm$0.68Improved
Add adversarial alignment of labeled and unlabeled feature distributions (ablation)Prediction-loss-only model · MHEALTHaccuracy: 86.67$\pm$0.67 -> 89.85$\pm$1.12Improved
Add adversarial alignment of labeled and unlabeled feature distributions (ablation)Prediction-loss-only model · OPPORTUNITYaccuracy: 48.56$\pm$0.62 -> 54.82$\pm$0.79Improved
Add reconstruction and latent consistency, without adversarial alignment (ablation)Prediction-loss-only model · EEGaccuracy: 66.62$\pm$0.83 -> 68.85$\pm$0.69Improved
Add reconstruction and latent consistency, without adversarial alignment (ablation)Prediction-loss-only model · EMGaccuracy: 64.56$\pm$1.15 -> 67.40$\pm$0.53Improved
Add reconstruction and latent consistency, without adversarial alignment (ablation)Prediction-loss-only model · MHEALTHaccuracy: 86.67$\pm$0.67 -> 87.41$\pm$1.33Improved
Add reconstruction and latent consistency, without adversarial alignment (ablation)Prediction-loss-only model · OPPORTUNITYaccuracy: 48.56$\pm$0.62 -> 51.85$\pm$0.92Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy