# Learning with Group Noise

arXiv: https://arxiv.org/abs/2103.09468 · HTML: https://mlsanity.com/paper/2103.09468/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 17 Mar 2021.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Are Anchor Points Really Indispensable in Label-Noise Learning?](https://mlsanity.com/paper/1906.00189/) (2019)
- [Recurrent Neural Networks with Top-k Gains for Session-based Recommendations](https://mlsanity.com/paper/1706.03847/) (2017)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning](https://mlsanity.com/paper/2006.07805/) (2020)
- [Distilling Knowledge from Graph Convolutional Networks](https://mlsanity.com/paper/2003.10477/) (2020)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey](https://mlsanity.com/paper/1912.05170/) (2019)
- [Masking: A New Perspective of Noisy Supervision](https://mlsanity.com/paper/1805.08193/) (2018)
- [Partial Label Learning with Self-Guided Retraining](https://mlsanity.com/paper/1902.03045/) (2019)
- [Deep Learning from Noisy Image Labels with Quality Embedding](https://mlsanity.com/paper/1711.00583/) (2017)
- [Part-dependent Label Noise: Towards Instance-dependent Label Noise](https://mlsanity.com/paper/2006.07836/) (2020)
- [A Regularization Approach for Instance-Based Superset Label Learning](https://mlsanity.com/paper/1904.02832/) (2019)
- [Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels](https://mlsanity.com/paper/2012.04193/) (2020)
- [Variational Collaborative Learning for User Probabilistic Representation](https://mlsanity.com/paper/1809.08400/) (2018)
- [Address Instance-level Label Prediction in Multiple Instance Learning](https://mlsanity.com/paper/1905.12226/) (2019)

## Built on by (most cited first, 5 of 5)

- [Sample Selection with Uncertainty of Losses for Learning with Noisy Labels](https://mlsanity.com/paper/2106.00445/) (2021)
- [Identifiability of Label Noise Transition Matrix](https://mlsanity.com/paper/2202.02016/) (2022)
- [Latent Class-Conditional Noise Model](https://mlsanity.com/paper/2302.09595/) (2023)
- [AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking](https://mlsanity.com/paper/2310.09706/) (2023)
- [Noisy Early Stopping for Noisy Labels](https://mlsanity.com/paper/2409.06830/) (2024)

## Abstract (arXiv)

Machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels. However, the group noise, which is parasitic on the coarse-grained accurate relation with the fine-grained uncertainty, is also universal and has not been well investigated. The challenge under this setting is how to discover true pairwise connections concealed by the group relation with its fine-grained noise. To overcome this issue, we propose a novel Max-Matching method for learning with group noise. Specifically, it utilizes a matching mechanism to evaluate the relation confidence of each object w.r.t. the target, meanwhile considering the Non-IID characteristics among objects in the group. Only the most confident object is considered to learn the model, so that the fine-grained noise is mostly dropped. The performance on arange of real-world datasets in the area of several learning paradigms demonstrates the effectiveness of Max-Matching