# PLM: Partial Label Masking for Imbalanced Multi-label Classification

arXiv: https://arxiv.org/abs/2105.10782 · HTML: https://mlsanity.com/paper/2105.10782/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 22 May 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Deep Learning based Recommender System: A Survey and New Perspectives](https://mlsanity.com/paper/1707.07435/) (2017)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [Striking the Right Balance with Uncertainty](https://mlsanity.com/paper/1901.07590/) (2019)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Semantic Regularisation for Recurrent Image Annotation](https://mlsanity.com/paper/1611.05490/) (2016)
- [Weakly Supervised Deep Image Hashing through Tag Embeddings](https://mlsanity.com/paper/1806.05804/) (2018)

## Built on by (most cited first, 10 of 10)

- [Gradient-Based Adversarial and Out-of-Distribution Detection](https://mlsanity.com/paper/2206.08255/) (2022)
- [Probing the Purview of Neural Networks via Gradient Analysis](https://mlsanity.com/paper/2304.02834/) (2023)
- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)
- [Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning](https://mlsanity.com/paper/2510.17520/) (2025)
- [HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid](https://mlsanity.com/paper/2410.06370/) (2024)
- [A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends](https://mlsanity.com/paper/2406.06119/) (2024)
- [EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion](https://mlsanity.com/paper/2412.07499/) (2024)
- [Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work](https://mlsanity.com/paper/2507.15823/) (2025)
- [Least-Ambiguous Multi-Label Classifier](https://mlsanity.com/paper/2509.10689/) (2025)
- [From Ambiguity to Action: A POMDP Perspective on Partial Multi-Label Ambiguity and Its Horizon-One Resolution](https://mlsanity.com/paper/2602.04255/) (2026)

## Abstract (arXiv)

Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class skews network output probabilities further from ground-truth distributions. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. By stochastically masking labels during loss computation, the method balances this ratio for each class, leading to improved recall on minority classes and improved precision on frequent classes. The ratio is estimated adaptively based on the network's performance by minimizing the KL divergence between predicted and ground-truth distributions. Whereas most existing approaches addressing data imbalance are mainly focused on single-label classification and do not generalize well to the multi-label case, this work proposes a general approach to solve the long-tail data imbalance issue for multi-label classification. PLM is versatile: it can be applied to most objective functions and it can be used alongside other strategies for class imbalance. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.