Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Biomedical Translation With Cycle Wasserstein Regression GANs
Matthew McDermott, Tom Yan, Tristan Naumann, Nathan Hunt, Harini Suresh, Peter Szolovits, Marzyeh Ghassemi
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 |
|---|---|---|---|
| add Wasserstein critic and cycle loss with unpaired data to MLP regression | MLP regressor · ICU ITE prediction (VENT, NOREP, PHEN, DOP) | median Euclidean loss: -0.50%, -7.4%, -4.5%, +2.7% | Mixed |
| use CWR-GAN with unpaired data instead of standard regressor when all data is paired | L1000 transcriptomics regression · L1000 100% paired | loss change vs standard regressor: 3.6% higher loss | Hurt |
| increase fraction of unpaired data (50% to 97%) for CWR-GAN versus standard regressor | CWR-GAN · L1000 transcriptomics | loss change vs standard regressor: 1.4% -> −0.3% -> −1.6% | Improved |
| add cycle loss alone to a bidirectional regressor (ablation) | bidirectional MLP regressor · ICU/biomedical regression | regression loss | No clear effect |
| use shorter 6 and 12 hour windows instead of 24 hour windows (ablation) | CWR-GAN · ICU ITE prediction | regression loss | Hurt |
Closest papers by meaning
- Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization (ICCV 2019 · similarity 0.86)
- On Translation and Reconstruction Guarantees of the Cycle-Consistent Generative Adversarial Networks (NeurIPS 2022 · similarity 0.85)
- Adversarial Transformations for Semi-Supervised Learning (AAAI 2020 · similarity 0.85)
- Semi-supervised Deep Transfer for Regression without Domain Alignment (ICCV 2025 · similarity 0.85)
- Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning (CVPR 2020 · similarity 0.84)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.83)
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.
