Research map / Learning theory and algorithms / Kernels and regression theory
Deep Active Learning by Leveraging Training Dynamics
Haonan Wang, Wei Huang, Ziwei Wu, Hanghang Tong, Andrew J Margenot, Jingrui He
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 |
|---|---|---|---|
| Increase query rounds from 1 to 10 at fixed total budget B=1000 | dynamicAL on CIFAR10+CNN · CIFAR10 | accuracy: 36.67 -> 36.84 | Improved |
| Increase query rounds from 1 to 10 at fixed total budget B=1000 | dynamicAL on CIFAR10+ResNet · CIFAR10 | accuracy: 40.09 -> 40.92 | Improved |
| Increase query rounds from 1 to 10 at fixed total budget B=1000 | dynamicAL on SVHN+VGG · SVHN | accuracy: 70.04 -> 76.34 | Improved |
| Increase query rounds from 1 to 10 at fixed total budget B=1000 | dynamicAL on Caltech101+ResNet · Caltech101 | accuracy: 33.82 -> 37.06 | Improved |
| Use gamma=2 in the acquisition criterion rather than the tested alternative gamma values (ablation) | dynamicAL · Active learning benchmarks shown in the variant comparison | test accuracy | Improved |
Closest papers by meaning
- Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer (ICML 2025 · similarity 0.87)
- Transductive Active Learning: Theory and Applications (NeurIPS 2024 · similarity 0.86)
- Deep Active Learning with a Neural Architecture Search (NeurIPS 2019 · similarity 0.86)
- On the training dynamics of deep networks with $L_2$ regularization (NeurIPS 2020 · similarity 0.86)
- Debiased Active Learning with Variational Gradient Rectifier (AAAI 2025 · similarity 0.85)
- A Dynamical Model of Neural Scaling Laws (ICML 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.
