Research map / Label-efficient and robust learning / Semi-supervised learning
Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
Aude Sportisse, Hugo Schmutz, Olivier HUMBERT, Charles Bouveyron, Pierre-Alexandre Mattei
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 class-specific missingness estimates and IPW instead of the original pseudo-label method | MNIST semi-supervised learning · MNIST (unbalanced labels) | test accuracy: 92.95 -> 94.83 | Improved |
| Use class-specific missingness estimates and IPW instead of the original pseudo-label method | MNIST semi-supervised learning · MNIST (unbalanced labels) | test loss: 0.141 -> 0.103 | Improved |
| Estimate class-specific label missingness and debias FixMatch with IPW | FixMatch · CIFAR-10 (informative labels) | test accuracy: 90.91 -> 91.88 | Improved |
| Estimate class-specific label missingness and debias FixMatch with IPW | FixMatch · CIFAR-10 (informative labels) | test loss: 0.426 -> 0.321 | Improved |
| Estimate the missing-data mechanism and debias with IPW instead of using pseudo-labeling alone | Semi-supervised learning · dermaMNIST (informative labels) | test accuracy: 57.72 -> 66.65 | Improved |
| Estimate the missing-data mechanism by maximum likelihood and use IPW | Semi-supervised learning · noduleMNIST3D (informative labels) | test accuracy: 84.91 -> 85.8 | Improved |
| Estimate class-specific label missingness rather than relying on class proportions | Semi-supervised learning · dermaMNIST (informative labels) | Accuracy Naevi: 66.14\pm 5.86 -> 93.54\pm2.30 | Improved |
| Use the moment estimator with gradients propagated through class proportions instead of the maximum-likelihood estimator | Semi-supervised learning · noduleMNIST3D (informative labels) | test accuracy: 85.8 -> 82.26 | Hurt |
Closest papers by meaning
- On Non-Random Missing Labels in Semi-Supervised Learning (ICLR 2022 · similarity 0.90)
- Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data (AAAI 2024 · similarity 0.87)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.87)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.86)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.86)
- Evaluating multiple models using labeled and unlabeled data (NeurIPS 2025 · similarity 0.85)
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.
