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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the full distributionally robust semi-supervised model instead of the strongest listed baseline | People-centric sensing recognition · EEG | accuracy: 73.29$\pm$0.68 -> 77.01$\pm$0.89 | Improved |
| Use the full distributionally robust semi-supervised model instead of the strongest listed baseline | People-centric sensing recognition · MHEALTH | accuracy: 92.08$\pm$0.53 -> 95.22$\pm$1.32 | Improved |
| Use the full distributionally robust semi-supervised model instead of the strongest listed baseline | People-centric sensing recognition · EMG | accuracy: 74.46$\pm$0.81 -> 77.83$\pm$0.56 | Improved |
| Use the full distributionally robust semi-supervised model instead of the strongest listed baseline | People-centric sensing recognition · OPPORTUNITY | accuracy: 59.23$\pm$1.72 -> 62.27$\pm$0.54 | Improved |
| Add adversarial alignment of labeled and unlabeled feature distributions (ablation) | Prediction-loss-only model · EEG | accuracy: 66.62$\pm$0.83 -> 70.79$\pm$0.81 | Improved |
| Add adversarial alignment of labeled and unlabeled feature distributions (ablation) | Prediction-loss-only model · EMG | accuracy: 64.56$\pm$1.15 -> 69.55$\pm$0.68 | Improved |
| Add adversarial alignment of labeled and unlabeled feature distributions (ablation) | Prediction-loss-only model · MHEALTH | accuracy: 86.67$\pm$0.67 -> 89.85$\pm$1.12 | Improved |
| Add adversarial alignment of labeled and unlabeled feature distributions (ablation) | Prediction-loss-only model · OPPORTUNITY | accuracy: 48.56$\pm$0.62 -> 54.82$\pm$0.79 | Improved |
| Add reconstruction and latent consistency, without adversarial alignment (ablation) | Prediction-loss-only model · EEG | accuracy: 66.62$\pm$0.83 -> 68.85$\pm$0.69 | Improved |
| Add reconstruction and latent consistency, without adversarial alignment (ablation) | Prediction-loss-only model · EMG | accuracy: 64.56$\pm$1.15 -> 67.40$\pm$0.53 | Improved |
| Add reconstruction and latent consistency, without adversarial alignment (ablation) | Prediction-loss-only model · MHEALTH | accuracy: 86.67$\pm$0.67 -> 87.41$\pm$1.33 | Improved |
| Add reconstruction and latent consistency, without adversarial alignment (ablation) | Prediction-loss-only model · OPPORTUNITY | accuracy: 48.56$\pm$0.62 -> 51.85$\pm$0.92 | Improved |
Closest papers by meaning
- Distribution-Based Semi-Supervised Learning for Activity Recognition (AAAI 2019 · similarity 0.86)
- Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions (ICML 2023 · similarity 0.84)
- Triplet Adaptation Framework for Robust Semi-Supervised Learning (TPAMI 2024 · similarity 0.83)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.83)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.82)
- Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning (AAAI 2025 · similarity 0.81)
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.
