Research map / Label-efficient and robust learning / Semi-supervised learning
AutoDAL: Distributed Active Learning with Automatic Hyperparameter Selection
Xu Chen, Brett Wujek
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 |
|---|---|---|---|
| automatically tune hyperparameters jointly instead of random values in distributed active learning | DAL · Breast cancer, 0.1% labeled | accuracy: at least 2% | Improved |
| tune only kernel width instead of all hyperparameters (ablation) | AutoDAL · Breast cancer, 0.1% labeled | accuracy: 3% vs 4.6% total | Improved |
| tune batch size (ablation) | AutoDAL · Diabetes | accuracy: around 2% of 2.4% total | Improved |
| tune batch size vs random selection (ablation) | AutoDAL · ECG | accuracy: 1.8% | Improved |
| tune kernel width (ablation) | AutoDAL · ECG | total accuracy: 0.7% | Improved |
| tune regularization parameter (ablation) | AutoDAL · ECG | total accuracy: 0.5% | Improved |
| use active learning instead of supervised AutoML when labeled data exceeds 5% | Auto-WEKA/Auto-sklearn vs AL methods · Benchmark datasets | accuracy | Hurt |
Closest papers by meaning
- A Unified Framework for Automatic Distributed Active Learning (TPAMI 2021 · similarity 0.93)
- Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement (ICML 2024 · similarity 0.81)
- AutoAL: Automated Active Learning with Differentiable Query Strategy Search (ICML 2025 · similarity 0.81)
- From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining (ICML 2025 · similarity 0.80)
- Combining Graph Transformers Based Multi-Label Active Learning and Informative Data Augmentation for Chest Xray Classification (AAAI 2024 · similarity 0.80)
- Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification (CVPR 2024 · similarity 0.79)
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.
