# Transfer and Marginalize: Explaining Away Label Noise with Privileged Information

arXiv: https://arxiv.org/abs/2202.09244 · HTML: https://mlsanity.com/paper/2202.09244/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 18 Feb 2022.

## Builds on (most cited first, 21 of 21)

- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [Correlated Input-Dependent Label Noise in Large-Scale Image Classification](https://mlsanity.com/paper/2105.10305/) (2021)
- [Deep Learning under Privileged Information Using Heteroscedastic Dropout](https://mlsanity.com/paper/1805.11614/) (2018)
- [A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?](https://mlsanity.com/paper/2012.03061/) (2020)
- [Privileged Features Distillation at Taobao Recommendations](https://mlsanity.com/paper/1907.05171/) (2019)
- [Learning Using Privileged Information: SVM+ and Weighted SVM](https://mlsanity.com/paper/1306.3161/) (2013)
- [Patterns for Learning with Side Information](https://mlsanity.com/paper/1511.06429/) (2015)
- [MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information](https://mlsanity.com/paper/1702.08681/) (2017)
- [Mind the Nuisance: Gaussian Process Classification using Privileged Noise](https://mlsanity.com/paper/1407.0179/) (2014)

## Built on by (most cited first, 15 of 15)

- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [Eliciting and Learning with Soft Labels from Every Annotator](https://mlsanity.com/paper/2207.00810/) (2022)
- [MathWriting: A Dataset For Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2404.10690/) (2024)
- [Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs](https://mlsanity.com/paper/2402.08733/) (2024)
- [Toward Understanding Privileged Features Distillation in Learning-to-Rank](https://mlsanity.com/paper/2209.08754/) (2022)
- [On Subjective Uncertainty Quantification and Calibration in Natural Language Generation](https://mlsanity.com/paper/2406.05213/) (2024)
- [When does Privileged Information Explain Away Label Noise?](https://mlsanity.com/paper/2303.01806/) (2023)
- [Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting](https://mlsanity.com/paper/2505.04733/) (2025)
- [Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels](https://mlsanity.com/paper/2310.06600/) (2023)
- [Rethinking Knowledge Transfer in Learning Using Privileged Information](https://mlsanity.com/paper/2408.14319/) (2024)
- [When are radiology reports useful for training medical image classifiers?](https://mlsanity.com/paper/2510.24385/) (2025)
- [Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach](https://mlsanity.com/paper/2605.07166/) (2026)
- [AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching](https://mlsanity.com/paper/2608.03047/) (2026)
- [TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration](https://mlsanity.com/paper/2608.10286/) (2026)
- [Quantifying the Value of Privileged Information Using a PAC-Bayesian Approach](https://mlsanity.com/paper/2609.12891/) (2026)

## Abstract (arXiv)

Supervised learning datasets often have privileged information, in the form of features which are available at training time but are not available at test time e.g. the ID of the annotator that provided the label. We argue that privileged information is useful for explaining away label noise, thereby reducing the harmful impact of noisy labels. We develop a simple and efficient method for supervised learning with neural networks: it transfers via weight sharing the knowledge learned with privileged information and approximately marginalizes over privileged information at test time. Our method, TRAM (TRansfer and Marginalize), has minimal training time overhead and has the same test-time cost as not using privileged information. TRAM performs strongly on CIFAR-10H, ImageNet and Civil Comments benchmarks.