# CAENL: Collapse-Based Active Neural Learning with Objective-Aligned Representation Control

arXiv: https://arxiv.org/abs/2610.17509 · HTML: https://mlsanity.com/paper/2610.17509/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [A Geometric Analysis of Neural Collapse with Unconstrained Features](https://mlsanity.com/paper/2105.02375/) (2021)
- [Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation](https://mlsanity.com/paper/1705.08475/) (2017)
- [Improved Image Captioning via Policy Gradient optimization of SPIDEr](https://mlsanity.com/paper/1612.00370/) (2016)
- [Deep Linear Discriminant Analysis](https://mlsanity.com/paper/1511.04707/) (2015)
- [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)
- [Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data](https://mlsanity.com/paper/2409.01832/) (2024)
- [Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers](https://mlsanity.com/paper/2505.15239/) (2025)
- [On the Robustness of Neural Collapse and the Neural Collapse of Robustness](https://mlsanity.com/paper/2311.07444/) (2023)
- [Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning](https://mlsanity.com/paper/2512.07844/) (2025)
- [Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learning](https://mlsanity.com/paper/2604.12303/) (2026)
- [Active Learning Using Aggregated Acquisition Functions: Accuracy and Sustainability Analysis](https://mlsanity.com/paper/2602.07440/) (2026)

## Abstract (arXiv)

Active learning changes the representations used to acquire subsequent labels. We study this interaction through Collapse-Based Active Neural Learning (CAENL), which separates acquisition, Dynamic Collapse Regularization (DCR), and its coefficient policy. DCR penalizes a normalized within-class to between-class scatter residual above a frozen reference, with a separate class-separation safeguard. Fixed, scheduled, deterministic-feedback, and learned-feedback policies apply this objective. The analysis establishes scatter invariances, conditional local descent, and coefficient bounds, and shows why clean geometry alone cannot guarantee input robustness. Six-seed classification comparisons are complemented by a 104-run study with separate control selection and ten-seed evaluations on each of two backbones. At 60% annotations on ImageNet-100, entropy acquisition with DCR and MACC-Lite reaches 73.420 +/- 0.512% accuracy on ResNet-50 and 73.086 +/- 0.397% on ResNet-18 (mean +/- seed SD), exceeding entropy alone by 1.742 and 1.834 percentage points. Both gains survive Holm correction under paired-t and exact sign-flip tests, with unchanged feedback settings across backbones. Independently tuned constants attain slightly higher mean accuracy; the paired comparisons establish neither adaptive superiority nor equivalence. Separate six-seed spectral studies yield a small fixed-regularization C4 loss reduction, worse CIFAR-10 diffusion FID, and inconclusive AudioCaps captioning effects. Earlier classification studies find near-zero AutoAttack accuracy at L-infinity radius 8/255 and no added benefit from learned control. The results support the evaluated combined classification treatment and identify the task dependence of geometry-informed regularization.