AutoAL: Automated Active Learning with Differentiable Query Strategy Search
Not on the map. Why?
Abstract (arXiv)
As deep learning continues to evolve, the need for data efficiency becomes increasingly important. Considering labeling large datasets is both time-consuming and expensive, active learning (AL) provides a promising solution to this challenge by iteratively selecting the most informative subsets of examples to train deep neural networks, thereby reducing the labeling cost. However, the effectiveness of different AL algorithms can vary significantly across data scenarios, and determining which AL algorithm best fits a given task remains a challenging problem. This work presents the first differentiable AL strategy search method, named AutoAL, which is designed on top of existing AL sampling strategies. AutoAL consists of two neural nets, named SearchNet and FitNet, which are optimized concurrently under a differentiable bi-level optimization framework. For any given task, SearchNet and FitNet are iteratively co-optimized using the labeled data, learning how well a set of candidate AL algorithms perform on that task. With the optimal AL strategies identified, SearchNet selects a small subset from the unlabeled pool for querying their annotations, enabling efficient training of the task model. Experimental results demonstrate that AutoAL consistently achieves superior accuracy compared to all candidate AL algorithms and other selective AL approaches, showcasing its potential for adapting and integrating multiple existing AL methods across diverse tasks and domains. Code is available at: https://github.com/haizailache999/AutoAL.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 17 Oct 2024.
Builds on
29 of 52 references.
References · 29
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2016An overview of gradient descent optimization algorithmscited by 1,021
- 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
- 2017Deep Bayesian Active Learning with Image Datacited by 812
- 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2020A Survey of Deep Active Learningcited by 547
- 2019Learning Loss for Active Learningcited by 335
17 more
- 2019Variational Adversarial Active Learningcited by 284
- 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
- 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
- 2021Batch Active Learning at Scalecited by 127
- 2019Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functionscited by 104
- 2022A Comparative Survey of Deep Active Learningcited by 88
- 2017Generative Adversarial Active Learningcited by 69
- 2022Gradient-based Bi-level Optimization for Deep Learning: A Surveycited by 26
- 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
- 2020TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Searchcited by 21
- 2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
- 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
- 2019LambdaOpt: Learn to Regularize Recommender Models in Finer Levelscited by 14
- 2021Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processescited by 9
- 2018Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advicecited by 6
- 2021Towards General and Efficient Active Learningcited by 6
- 2023Rapid Image Labeling via Neuro-Symbolic Learningcited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.