Research map / Learning theory and algorithms / Prediction and decision losses
Batch Active Learning at Scale
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 |
|---|---|---|---|
| add HAC-cluster diversification of low-margin examples (Cluster-Margin vs Margin) (ablation) | Margin sampling · Open Images v6, batch 1M | labels needed for same pooled AP: 37% of Margin's labels | Helped |
| add HAC-cluster diversification of low-margin examples (Cluster-Margin vs Margin) (ablation) | Margin sampling · Open Images v6, batch 100K | labels needed for same pooled AP: 71% of Margin's labels | Helped |
| Cluster-Margin vs Margin sampling | batch active learning · SVHN, batch 5K | accuracy | No clear effect |
| Cluster-Margin vs baselines | VGG16 active learning · CIFAR10, CIFAR100 | accuracy | Helped |
| use approximate CoreSet (k-center) instead of random sampling | VGG16 active learning · CIFAR10, CIFAR100, SVHN | accuracy | No clear effect |
Closest papers by meaning
- Bayesian Batch Active Learning as Sparse Subset Approximation (NeurIPS 2019 · similarity 0.93)
- Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing (ICLR 2023 · similarity 0.91)
- Scaling Up Active Testing to Large Language Models (NeurIPS 2025 · similarity 0.88)
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 2025 · similarity 0.87)
- One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models (ICLR 2024 · similarity 0.87)
- Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training (NeurIPS 2025 · similarity 0.87)
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.