Research map / Architectures and efficiency / Neural architecture search
Deep Active Learning with a Neural Architecture Search
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 |
|---|---|---|---|
| search for the architecture incrementally during active learning instead of using a fixed architecture | active learning with softmax response, MC-dropout, or coreset · CIFAR-10 | accuracy | Helped |
| search for the architecture incrementally during active learning instead of using a fixed architecture | active learning with softmax response, MC-dropout, or coreset · CIFAR-100 | accuracy | Helped |
| search for the architecture incrementally during active learning instead of using a fixed architecture | active learning with softmax response, MC-dropout, or coreset · SVHN | accuracy | Helped |
| use Resnet-18 instead of the small A(B_r,1,2) architecture | fixed-architecture active learning · CIFAR-10, early active-learning rounds | accuracy | Hurt |
| use Resnet-18 instead of the small A(B_r,1,2) architecture | fixed-architecture active learning · CIFAR-10, later active-learning rounds | accuracy | Helped |
| use softmax response rather than MC-dropout or coreset | active-iNAS · CIFAR-10, CIFAR-100, and SVHN | accuracy | Helped |
| use MC-dropout rather than softmax response | active-iNAS · CIFAR-100 | accuracy | Hurt |
| use coreset rather than softmax response | active-iNAS · CIFAR-10, CIFAR-100, and SVHN | accuracy | Hurt |
| use the small A(B_r,1,2) architecture rather than Resnet-18 | softmax-response active learning · CIFAR-10, early labeling budgets | AUC-GAIN | Helped |
| use the small A(B_r,1,2) architecture rather than Resnet-18 | softmax-response active learning · CIFAR-10, later labeling budgets | AUC-GAIN | Hurt |
Closest papers by meaning
- AutoAL: Automated Active Learning with Differentiable Query Strategy Search (ICML 2025 · similarity 0.85)
- Insights from the Use of Previously Unseen Neural Architecture Search Datasets (CVPR 2024 · similarity 0.85)
- Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples (ICML 2024 · similarity 0.85)
- Neural Active Learning Beyond Bandits (ICLR 2024 · similarity 0.85)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 2024 · similarity 0.85)
- Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes (ICML 2025 · 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.