# Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data

arXiv: https://arxiv.org/abs/2301.05106 · HTML: https://mlsanity.com/paper/2301.05106/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 12 Jan 2023.

## Builds on (most cited first, 16 of 16)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1805.07810/) (2018)
- [Discriminative Active Learning](https://mlsanity.com/paper/1907.06347/) (2019)
- [SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios](https://mlsanity.com/paper/2107.00717/) (2021)
- [Gradients as a Measure of Uncertainty in Neural Networks](https://mlsanity.com/paper/2008.08030/) (2020)
- [Backpropagated Gradient Representations for Anomaly Detection](https://mlsanity.com/paper/2007.09507/) (2020)
- [CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition](https://mlsanity.com/paper/1712.02463/) (2017)
- [Novelty Detection Through Model-Based Characterization of Neural Networks](https://mlsanity.com/paper/2008.06094/) (2020)
- [Contrastive Reasoning in Neural Networks](https://mlsanity.com/paper/2103.12329/) (2021)
- [On Warm-Starting Neural Network Training](https://mlsanity.com/paper/1910.08475/) (2019)
- [Man-recon: manifold learning for reconstruction with deep autoencoder for smart seismic interpretation](https://mlsanity.com/paper/2212.07568/) (2022)
- [Explaining Deep Models through Forgettable Learning Dynamics](https://mlsanity.com/paper/2301.04221/) (2023)
- [On the Structures of Representation for the Robustness of Semantic Segmentation to Input Corruption](https://mlsanity.com/paper/2009.00817/) (2020)

## Built on by (most cited first, 8 of 8)

- [Gaussian Switch Sampling: A Second Order Approach to Active Learning](https://mlsanity.com/paper/2302.12018/) (2023)
- [FOCAL: A Cost-Aware Video Dataset for Active Learning](https://mlsanity.com/paper/2311.10591/) (2023)
- [AHA: Human-Assisted Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2410.08000/) (2024)
- [Out-of-Distribution Learning with Human Feedback](https://mlsanity.com/paper/2408.07772/) (2024)
- [Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks](https://mlsanity.com/paper/2302.05776/) (2023)
- [Benchmarking of Query Strategies: Towards Future Deep Active Learning](https://mlsanity.com/paper/2312.05751/) (2023)
- [Targeting Negative Flips in Active Learning using Validation Sets](https://mlsanity.com/paper/2411.10896/) (2024)
- [Effective Data Selection for Seismic Interpretation through Disagreement](https://mlsanity.com/paper/2406.05149/) (2024)

## Abstract (arXiv)

This paper considers deep out-of-distribution active learning. In practice, fully trained neural networks interact randomly with out-of-distribution (OOD) inputs and map aberrant samples randomly within the model representation space. Since data representations are direct manifestations of the training distribution, the data selection process plays a crucial role in outlier robustness. For paradigms such as active learning, this is especially challenging since protocols must not only improve performance on the training distribution most effectively but further render a robust representation space. However, existing strategies directly base the data selection on the data representation of the unlabeled data which is random for OOD samples by definition. For this purpose, we introduce forgetful active learning with switch events (FALSE) - a novel active learning protocol for out-of-distribution active learning. Instead of defining sample importance on the data representation directly, we formulate "informativeness" with learning difficulty during training. Specifically, we approximate how often the network "forgets" unlabeled samples and query the most "forgotten" samples for annotation. We report up to 4.5% accuracy improvements in over 270 experiments, including four commonly used protocols, two OOD benchmarks, one in-distribution benchmark, and three different architectures.