# OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models

arXiv: https://arxiv.org/abs/2609.03972 · HTML: https://mlsanity.com/paper/2609.03972/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Machine Unlearning: Linear Filtration for Logit-based Classifiers](https://mlsanity.com/paper/2002.02730/) (2020)
- [Deep Unlearning via Randomized Conditionally Independent Hessians](https://mlsanity.com/paper/2204.07655/) (2022)
- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [PUMA: Performance Unchanged Model Augmentation for Training Data Removal](https://mlsanity.com/paper/2203.00846/) (2022)
- [Algorithms that Approximate Data Removal: New Results and Limitations](https://mlsanity.com/paper/2209.12269/) (2022)
- [Coded Machine Unlearning](https://mlsanity.com/paper/2012.15721/) (2020)
- [Recommendation Unlearning via Influence Function](https://mlsanity.com/paper/2307.02147/) (2023)
- [Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models](https://mlsanity.com/paper/2312.14923/) (2023)
- [Cross-Platform E-Commerce Product Categorization and Recategorization: A Multimodal Hierarchical Classification Approach](https://mlsanity.com/paper/2508.20013/) (2025)

## Abstract (arXiv)

Label removal occurs frequently in classification systems with evolving taxonomies, where categories must be dynamically updated or eliminated. To accommodate such changes, classification models must adapt accordingly. Existing solutions, broadly categorized as retraining-based and feature-space-adjustment-based, share common limitations despite their variations, including reliance on access to original data, substantial computational and storage costs, inconsistent results, poor scalability, and degradation of model utility. To address this, we propose a novel approach that leverages statistical redistribution in the output space to approximate the post-removal confidence vectors of a retrained model. Applicable as a modular output filter, our method bypasses the burden of feature-space adjustments or loss-function convergence, alleviating scalability limitations. Furthermore, by requiring only existing labels and prior output confidences, the method potentially mitigates privacy concerns inherent to data-dependent solutions. Extensive experiments demonstrate competitive performance against full retraining, with improvements in computational efficiency and privacy preservation across several classification tasks.