# A Mechanism-Driven Theory of Phase Transitions in Active Learning

arXiv: https://arxiv.org/abs/2607.00144 · HTML: https://mlsanity.com/paper/2607.00144/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [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)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [Gone Fishing: Neural Active Learning with Fisher Embeddings](https://mlsanity.com/paper/2106.09675/) (2021)
- [Active Learning Through a Covering Lens](https://mlsanity.com/paper/2205.11320/) (2022)
- [Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision](https://mlsanity.com/paper/1901.01151/) (2019)
- [Skin Lesion Classification Using Ensembles of Multi-Resolution EfficientNets with Meta Data](https://mlsanity.com/paper/1910.03910/) (2019)
- [A Unified Approach to Coreset Learning](https://mlsanity.com/paper/2111.03044/) (2021)
- [Uncertainty Herding: One Active Learning Method for All Label Budgets](https://mlsanity.com/paper/2412.20644/) (2024)
- [Active Distance-Based Clustering using K-medoids](https://mlsanity.com/paper/1512.03953/) (2015)
- [Bounds on the Generalization Error in Active Learning](https://mlsanity.com/paper/2409.09078/) (2024)

## Built on by (most cited first, 1 of 1)

- [How Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classification](https://mlsanity.com/paper/2608.03511/) (2026)

## Abstract (arXiv)

Active learning (AL) performance is known to be budget-dependent, yet regimes are typically defined by heuristic label counts that fail to generalize across datasets or architectures. We characterize AL dynamics by reframing budget regimes as shifts in the dominant generalization mechanism. By reinterpreting PAC-style risk components as dynamic interacting terms, we prove that dominance shifts are structurally unavoidable, creating a moving bottleneck for generalization. We operationalize this using measurable proxies and a segmented regression procedure to identify a tripartite taxonomy: data-driven, transition, and model-driven phases. Our framework explains the long-standing observation that representativeness, coverage, and uncertainty strategies excel at different stages. Experiments across natural and medical imaging show that AL efficiency depends on the alignment between the strategy's inductive bias and the active bottleneck. Moreover, self-supervised representation shift transitions earlier along the labeling trajectory, highlighting the role of representation quality in shaping AL dynamics. Overall, this work provides a unified framework for the next generation of transition-aware AL algorithms.