Research map / Label-efficient and robust learning / Semi-supervised learning
Towards Automated Semi-Supervised Learning
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 AUTO-SSL instead of supervised AutoML (AUTO-SKLEARN) | AUTO-SSL · 40 datasets, 20 labeled | accuracy (%): 74.8 -> 76.9 | Helped |
| use AUTO-SSL instead of classical SSL (TSVM) | AUTO-SSL · 40 datasets, 20 labeled | accuracy (%): 75.0 -> 76.9 | Helped |
| use AUTO-SSL instead of plain SVM on labeled data | AUTO-SSL · 40 datasets, 20 labeled | AUC (%): 78.6 -> 78.9 | No clear effect |
| classical SSL (TSVM) versus SVM | TSVM · 40 datasets, 20 labeled | accuracy (%): 76.0 -> 75.0 | Hurt |
| use AUTO-SSL instead of TSVM for reliability vs SVM | AUTO-SSL · Win/Tie/Loss vs SVM, accuracy, 20 labeled | Win/Tie/Loss: 12/15/13 -> 11/25/4 | Helped |
Closest papers by meaning
- Pipeline Combinators for Gradual AutoML (NeurIPS 2021 · similarity 0.87)
- An ADMM Based Framework for AutoML Pipeline Configuration (AAAI 2020 · similarity 0.87)
- Learning meta-features for AutoML (ICLR 2022 · similarity 0.86)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.85)
- AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks (AAAI 2025 · similarity 0.85)
- Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning (ICML 2024 · 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.