Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Dependency Structures for Weak Supervision 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 |
|---|---|---|---|
| Learn dependencies with robust PCA instead of using Bach et al.'s learned dependencies | Weak supervision generative model and downstream classifier · Bone Tumor | F1: +4.13 | Helped |
| Learn dependencies with robust PCA instead of using Bach et al.'s learned dependencies | Weak supervision generative model and downstream classifier · CDR | F1: +0.91 | Helped |
| Learn dependencies with robust PCA instead of using Bach et al.'s learned dependencies | Weak supervision generative model and downstream classifier · IMDb | F1: +2.48 | Helped |
| Learn dependencies with robust PCA instead of using Bach et al.'s learned dependencies | Weak supervision generative model and downstream classifier · MS-COCO | F1: +4.41 | Helped |
| Model learned dependencies instead of assuming conditional independence | Weak supervision generative model and downstream classifier · Bone Tumor | F1: +4.64 | Helped |
| Model learned dependencies instead of assuming conditional independence | Weak supervision generative model and downstream classifier · CDR | F1: +2.21 | Helped |
| Model learned dependencies instead of assuming conditional independence | Weak supervision generative model and downstream classifier · IMDb | F1: +3.91 | Helped |
| Model learned dependencies instead of assuming conditional independence | Weak supervision generative model and downstream classifier · MS-COCO | F1: +4.41 | Helped |
Closest papers by meaning
- Training Complex Models with Multi-Task Weak Supervision (AAAI 2019 · similarity 0.91)
- Learning from weak labelers as constraints (ICLR 2025 · similarity 0.91)
- A General Framework for Learning from Weak Supervision (ICML 2024 · similarity 0.88)
- Weak Supervision Performance Evaluation via Partial Identification (NeurIPS 2024 · similarity 0.87)
- Limited-Supervised Multi-Label Learning with Dependency Noise (AAAI 2024 · similarity 0.86)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.86)
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.