# Active learning for imbalanced data under cold start

arXiv: https://arxiv.org/abs/2107.07724 · HTML: https://mlsanity.com/paper/2107.07724/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 35 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 6 of 6)

- [Discriminative Active Learning](https://mlsanity.com/paper/1907.06347/) (2019)
- [Aleatoric and Epistemic Uncertainty with Random Forests](https://mlsanity.com/paper/2001.00893/) (2020)
- [A Benchmark and Comparison of Active Learning for Logistic Regression](https://mlsanity.com/paper/1611.08618/) (2016)
- [Interleaved Sequence RNNs for Fraud Detection](https://mlsanity.com/paper/2002.05988/) (2020)
- [Streaming Active Learning Strategies for Real-Life Credit Card Fraud Detection: Assessment and Visualization](https://mlsanity.com/paper/1804.07481/) (2018)
- [Online Adaptive Asymmetric Active Learning with Limited Budgets](https://mlsanity.com/paper/1911.07498/) (2019)

## Built on by (most cited first, 5 of 5)

- [Fairness-Aware Data Valuation for Supervised Learning](https://mlsanity.com/paper/2303.16963/) (2023)
- [Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation](https://mlsanity.com/paper/2412.06470/) (2024)
- [STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning](https://mlsanity.com/paper/2402.13468/) (2024)
- [Dynamic Class-Aware Active Learning for Unbiased Satellite Image Segmentation](https://mlsanity.com/paper/2604.08965/) (2026)
- [Transfer Learning for Evolving Domains](https://mlsanity.com/paper/2609.13039/) (2026)

## Abstract (arXiv)

Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even worse in imbalanced data scenarios, where labels of the positive class take longer to accumulate. We propose an Active Learning (AL) system for datasets with orders of magnitude of class imbalance, in a cold start streaming scenario. We present a computationally efficient Outlier-based Discriminative AL approach (ODAL) and design a novel 3-stage sequence of AL labeling policies where ODAL is used as warm-up. Then, we perform empirical studies in four real world datasets, with various magnitudes of class imbalance. The results show that our method can more quickly reach a high performance model than standard AL policies without ODAL warm-up. Its observed gains over random sampling can reach 80% and be competitive with policies with an unlimited annotation budget or additional historical data (using just 2% to 10% of the labels).