Data to 7 Oct 2026

Gone Fishing: Neural Active Learning with Fisher Embeddings

arXiv 2106.09675 ↗First posted 17 Jun 2021cs.LGcited by 88

Not on the map. Why?

Abstract (arXiv)

There is an increasing need for effective active learning algorithms that are compatible with deep neural networks. This paper motivates and revisits a classic, Fisher-based active selection objective, and proposes BAIT, a practical, tractable, and high-performing algorithm that makes it viable for use with neural models. BAIT draws inspiration from the theoretical analysis of maximum likelihood estimators (MLE) for parametric models. It selects batches of samples by optimizing a bound on the MLE error in terms of the Fisher information, which we show can be implemented efficiently at scale by exploiting linear-algebraic structure especially amenable to execution on modern hardware. Our experiments demonstrate that BAIT outperforms the previous state of the art on both classification and regression problems, and is flexible enough to be used with a variety of model architectures.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Builds on 11 of its 56 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

11 of 56 references.

References · 11

2017Deep Bayesian Active Learning with Image Datacited by 812
2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 150
2019Discriminative Active Learningcited by 97
2017Deep Active Learning over the Long Tailcited by 82
2015A Century of Portraits: A Visual Historical Record of American High School Yearbookscited by 54
2015Convergence Rates of Active Learning for Maximum Likelihood Estimationcited by 25
2016Asymptotic Analysis of Objectives based on Fisher Information in Active Learningcited by 14
2020Learning Composable Energy Surrogates for PDE Order Reductioncited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 12; 2023: 16; 2024: 25; 2025: 11; 2026: 20.

88 papers.

Sort:

By area:

2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 63
2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 47
2021Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learningcited by 36
2023A comprehensive survey on deep active learning in medical image analysiscited by 32
2022GALAXY: Graph-based Active Learning at the Extremecited by 29
2022Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantitiescited by 28
2022A Lagrangian Duality Approach to Active Learningcited by 24
2021Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outlierscited by 22
2024An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Modelscited by 22
2024Active Learning for Neural PDE Solverscited by 22
2023Streaming Active Learning with Deep Neural Networkscited by 20
2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20

38 more

2024CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-trainingcited by 20
2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
2025From Selection to Generation: A Survey of LLM-based Active Learningcited by 18
2024Optimal Design for Human Preference Elicitationcited by 17
2022Deep Active Learning with Noise Stabilitycited by 13
2022Active Learning with Neural Networks: Insights from Nonparametric Statisticscited by 13
2023KECOR: Kernel Coding Rate Maximization for Active 3D Object Detectioncited by 13
2023Black-Box Batch Active Learning for Regressioncited by 12
2024Uncertainty Herding: One Active Learning Method for All Label Budgetscited by 12
2022Improved Algorithms for Neural Active Learningcited by 11
2024Neural Active Learning Beyond Banditscited by 10
2024Generative Active Learning for Long-tailed Instance Segmentationcited by 10
2025Active Learning for Direct Preference Optimizationcited by 9
2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
2021Anti-Concentrated Confidence Bonuses for Scalable Explorationcited by 7
2024Querying Easily Flip-flopped Samples for Deep Active Learningcited by 7
2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
2021Multi-Domain Active Learning: Literature Review and Comparative Studycited by 6
2022Neural Design for Genetic Perturbation Experimentscited by 6
2023Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learningcited by 6
2024Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classificationcited by 6
2024Active Preference Learning for Ordering Items In- and Out-of-samplecited by 6
2025Towards Active Synthetic Data Generation for Finetuning Language Modelscited by 6
2022Neural Active Learning on Heteroskedastic Distributionscited by 5
2024Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learningcited by 5
2024Bayesian Active Learning for Semantic Segmentationcited by 5
2024Deep Active Learning in the Open Worldcited by 5
2025Active Learning for Continual Learning: Keeping the Past Alive in the Presentcited by 5
2023Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verificationcited by 4
2024Learning from the Best: Active Learning for Wireless Communicationscited by 4
2024FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Informationcited by 3
2024Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimationcited by 3
2025Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspectivecited by 3
2025Towards Multimodal Active Learning: Efficient Learning with Limited Paired Datacited by 3
2023BatchGFN: Generative Flow Networks for Batch Active Learningcited by 2
2024Bayesian Active Learning for Censored Regressioncited by 2
2024Deep Active Learning with Manifold-preserving Trajectory Samplingcited by 2
2024COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptationcited by 2

50 most cited of 88 All 88 (JSON)