# Label Denoising through Cross-Model Agreement

arXiv: https://arxiv.org/abs/2308.13976 · HTML: https://mlsanity.com/paper/2308.13976/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 69 references that are in the map.
- First posted on arXiv 27 Aug 2023.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [SELF: Learning to Filter Noisy Labels with Self-Ensembling](https://mlsanity.com/paper/1910.01842/) (2019)
- [Deep Learning Based Text Classification: A Comprehensive Review](https://mlsanity.com/paper/2004.03705/) (2020)
- [Fast Matrix Factorization for Online Recommendation with Implicit Feedback](https://mlsanity.com/paper/1708.05024/) (2017)
- [Managing Popularity Bias in Recommender Systems with Personalized Re-ranking](https://mlsanity.com/paper/1901.07555/) (2019)
- [Denoising Implicit Feedback for Recommendation](https://mlsanity.com/paper/2006.04153/) (2020)
- [RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback](https://mlsanity.com/paper/1912.11160/) (2019)
- [Deep Learning in Bioinformatics](https://mlsanity.com/paper/1603.06430/) (2016)
- [Reinforced Negative Sampling over Knowledge Graph for Recommendation](https://mlsanity.com/paper/2003.05753/) (2020)
- [Meta-learning with an Adaptive Task Scheduler](https://mlsanity.com/paper/2110.14057/) (2021)
- [Self-Guided Learning to Denoise for Robust Recommendation](https://mlsanity.com/paper/2204.06832/) (2022)
- [Addressing Marketing Bias in Product Recommendations](https://mlsanity.com/paper/1912.01799/) (2019)
- [Multi-sided Exposure Bias in Recommendation](https://mlsanity.com/paper/2006.15772/) (2020)
- [Sampler Design for Implicit Feedback Data by Noisy-label Robust Learning](https://mlsanity.com/paper/2007.07204/) (2020)
- [Controlling Bias Exposure for Fair Interpretable Predictions](https://mlsanity.com/paper/2210.07455/) (2022)
- [Learning Robust Recommenders through Cross-Model Agreement](https://mlsanity.com/paper/2105.09605/) (2021)

## Abstract (arXiv)

Learning from corrupted labels is very common in real-world machine-learning applications. Memorizing such noisy labels could affect the learning of the model, leading to sub-optimal performances. In this work, we propose a novel framework to learn robust machine-learning models from noisy labels. Through an empirical study, we find that different models make relatively similar predictions on clean examples, while the predictions on noisy examples vary much more across different models. Motivated by this observation, we propose em denoising with cross-model agreement em (DeCA) which aims to minimize the KL-divergence between the true label distributions parameterized by two machine learning models while maximizing the likelihood of data observation. We employ the proposed DeCA on both the binary label scenario and the multiple label scenario. For the binary label scenario, we select implicit feedback recommendation as the downstream task and conduct experiments with four state-of-the-art recommendation models on four datasets. For the multiple-label scenario, the downstream application is image classification on two benchmark datasets. Experimental results demonstrate that the proposed methods significantly improve the model performance compared with normal training and other denoising methods on both binary and multiple-label scenarios.