Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning From Crowds Using Deep Generative Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 unlabeled data in the proposed model (ablation) | Proposed · MNIST PC labeling | accuracy: 0.7023 -> 0.9646 | Helped |
| use unlabeled data in the proposed model (ablation) | Proposed · MNIST DS labeling | accuracy: 0.5563 -> 0.8647 | Helped |
| use unlabeled data in the proposed model (ablation) | Proposed · Rotten Tomatoes | accuracy: 0.7262 -> 0.7290 | Helped |
| model labeling process with latent features (proposed vs M2 using averaged labels) | M2 · MNIST PC labeling | accuracy: 0.9421 -> 0.9646 | Helped |
| model labeling process with latent features (proposed vs M2) | M2 · Rotten Tomatoes | accuracy: 0.7096 -> 0.7290 | Helped |
| add graph-Laplacian prior to PC model | PC · MNIST | accuracy: 0.7756 -> 0.7754 | No clear effect |
Closest papers by meaning
- Deep Learning from Crowds (AAAI 2018 · similarity 0.90)
- Unbiased Multi-Label Learning from Crowdsourced Annotations (ICML 2024 · similarity 0.87)
- TLLC: Transfer Learning-based Label Completion for Crowdsourcing (ICML 2025 · similarity 0.86)
- KFNN: K-Free Nearest Neighbor For Crowdsourcing (NeurIPS 2024 · similarity 0.86)
- Coupled Confusion Correction: Learning from Crowds with Sparse Annotations (AAAI 2024 · similarity 0.85)
- Label Distribution Propagation-based Label Completion for Crowdsourcing (ICML 2025 · similarity 0.84)
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.