# Gone Fishing: Neural Active Learning with Fisher Embeddings

arXiv: https://arxiv.org/abs/2106.09675 · HTML: https://mlsanity.com/paper/2106.09675/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 56 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Adversarial Active Learning for Deep Networks: a Margin Based Approach](https://mlsanity.com/paper/1802.09841/) (2018)
- [A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1910.02923/) (2019)
- [Discriminative Active Learning](https://mlsanity.com/paper/1907.06347/) (2019)
- [Deep Active Learning over the Long Tail](https://mlsanity.com/paper/1711.00941/) (2017)
- [A Century of Portraits: A Visual Historical Record of American High School Yearbooks](https://mlsanity.com/paper/1511.02575/) (2015)
- [Convergence Rates of Active Learning for Maximum Likelihood Estimation](https://mlsanity.com/paper/1506.02348/) (2015)
- [Asymptotic Analysis of Objectives based on Fisher Information in Active Learning](https://mlsanity.com/paper/1605.08798/) (2016)
- [Learning Composable Energy Surrogates for PDE Order Reduction](https://mlsanity.com/paper/2005.06549/) (2020)

## Built on by (most cited first, 30 of 88)

- [FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information](https://mlsanity.com/paper/2311.17874/) (2023)
- [A Framework and Benchmark for Deep Batch Active Learning for Regression](https://mlsanity.com/paper/2203.09410/) (2022)
- [Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning](https://mlsanity.com/paper/2106.12059/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [GALAXY: Graph-based Active Learning at the Extreme](https://mlsanity.com/paper/2202.01402/) (2022)
- [Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities](https://mlsanity.com/paper/2208.00549/) (2022)
- [A Lagrangian Duality Approach to Active Learning](https://mlsanity.com/paper/2202.04108/) (2022)
- [An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models](https://mlsanity.com/paper/2401.06692/) (2024)
- [Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers](https://mlsanity.com/paper/2106.11719/) (2021)
- [Active Learning for Neural PDE Solvers](https://mlsanity.com/paper/2408.01536/) (2024)
- [Streaming Active Learning with Deep Neural Networks](https://mlsanity.com/paper/2303.02535/) (2023)
- [LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning](https://mlsanity.com/paper/2306.09910/) (2023)
- [CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training](https://mlsanity.com/paper/2406.10670/) (2024)
- [From Selection to Generation: A Survey of LLM-based Active Learning](https://mlsanity.com/paper/2502.11767/) (2025)
- [Algorithm Selection for Deep Active Learning with Imbalanced Datasets](https://mlsanity.com/paper/2302.07317/) (2023)
- [Optimal Design for Human Preference Elicitation](https://mlsanity.com/paper/2404.13895/) (2024)
- [Uncertainty Herding: One Active Learning Method for All Label Budgets](https://mlsanity.com/paper/2412.20644/) (2024)
- [Deep Active Learning with Noise Stability](https://mlsanity.com/paper/2205.13340/) (2022)
- [Active Learning with Neural Networks: Insights from Nonparametric Statistics](https://mlsanity.com/paper/2210.08367/) (2022)
- [KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection](https://mlsanity.com/paper/2307.07942/) (2023)
- [Black-Box Batch Active Learning for Regression](https://mlsanity.com/paper/2302.08981/) (2023)
- [Improved Algorithms for Neural Active Learning](https://mlsanity.com/paper/2210.00423/) (2022)
- [Neural Active Learning Beyond Bandits](https://mlsanity.com/paper/2404.12522/) (2024)
- [Generative Active Learning for Long-tailed Instance Segmentation](https://mlsanity.com/paper/2406.02435/) (2024)
- [Active Learning for Direct Preference Optimization](https://mlsanity.com/paper/2503.01076/) (2025)
- [Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation](https://mlsanity.com/paper/2312.09196/) (2023)
- [Anti-Concentrated Confidence Bonuses for Scalable Exploration](https://mlsanity.com/paper/2110.11202/) (2021)
- [Querying Easily Flip-flopped Samples for Deep Active Learning](https://mlsanity.com/paper/2401.09787/) (2024)
- [AHA: Human-Assisted Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2410.08000/) (2024)
- [Multi-Domain Active Learning: Literature Review and Comparative Study](https://mlsanity.com/paper/2106.13516/) (2021)

## 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.