Research map / Probabilistic and scientific modeling / Bayesian optimization
Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing
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 Batch-BALanCe instead of the compared baselines | MNIST, small-batch active learning · MNIST | accuracy | Helped |
| Use Batch-BALanCe instead of the compared baselines | Repeated-MNIST, batch size 10 · Repeated-MNIST | accuracy | Helped |
| Use Batch-BALanCe instead of random selection | Fashion-MNIST, batch size 10 · Fashion-MNIST | accuracy | Helped |
| Use Batch-BALanCe instead of BatchBALD | EMNIST-Balanced, batch size 5 · EMNIST-Balanced | accuracy | Helped |
| Use BALanCe or Batch-BALanCe instead of BatchBALD | Unbalanced EMNIST settings · EMNIST-ByMerge and EMNIST-ByClass | accuracy | Helped |
| Use Batch-BALanCe rather than the compared methods | Large-batch active learning with MC dropout · CIFAR-10 | accuracy | Helped |
| Use Batch-BALanCe with cSG-MCMC rather than the compared methods | CIFAR-10, batch size 5,000 · CIFAR-10 | accuracy | Helped |
| Use Batch-BALanCe instead of PowerBALD, Power-BALanCe, or BADGE | Large-batch active learning with MC dropout · SVHN | accuracy | No clear effect |
| Add acquisition-function-driven clustering to Power-BALanCe | Large-batch active learning · Active-learning benchmarks | accuracy | Helped |
| Explicitly partition sampled hypotheses into equivalence classes (ablation) | BALanCe · Active-learning experiments | accuracy | Hurt |
Closest papers by meaning
- Bayesian Batch Active Learning as Sparse Subset Approximation (NeurIPS 2019 · similarity 0.91)
- Batch Active Learning at Scale (NeurIPS 2021 · similarity 0.91)
- BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning (NeurIPS 2019 · similarity 0.91)
- Transductive Active Learning: Theory and Applications (NeurIPS 2024 · similarity 0.86)
- One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models (ICLR 2024 · similarity 0.85)
- Active Learning Guided by Efficient Surrogate Learners (AAAI 2024 · similarity 0.85)
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.