# Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning

arXiv: https://arxiv.org/abs/2509.17971 · HTML: https://mlsanity.com/paper/2509.17971/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 22 Sep 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [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)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Data Augmentation Can Improve Robustness](https://mlsanity.com/paper/2111.05328/) (2021)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Remix: Rebalanced Mixup](https://mlsanity.com/paper/2007.03943/) (2020)
- [BYOL works even without batch statistics](https://mlsanity.com/paper/2010.10241/) (2020)
- [Learning with Biased Complementary Labels](https://mlsanity.com/paper/1711.09535/) (2017)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Complementary-Label Learning for Arbitrary Losses and Models](https://mlsanity.com/paper/1810.04327/) (2018)
- [Learning with Multiple Complementary Labels](https://mlsanity.com/paper/1912.12927/) (2019)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels](https://mlsanity.com/paper/2007.02235/) (2020)
- [Binary Classification from Positive-Confidence Data](https://mlsanity.com/paper/1710.07138/) (2017)
- [GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering](https://mlsanity.com/paper/2210.15721/) (2022)
- [Bridging Ordinary-Label Learning and Complementary-Label Learning](https://mlsanity.com/paper/2002.02158/) (2020)
- [Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical](https://mlsanity.com/paper/2311.15502/) (2023)
- [Reduction from Complementary-Label Learning to Probability Estimates](https://mlsanity.com/paper/2209.09500/) (2022)
- [CLImage: Human-Annotated Datasets for Complementary-Label Learning](https://mlsanity.com/paper/2305.08295/) (2023)
- [Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models](https://mlsanity.com/paper/2001.04243/) (2020)
- [Global Mixup: Eliminating Ambiguity with Clustering](https://mlsanity.com/paper/2206.02734/) (2022)
- [libcll: an Extendable Python Toolkit for Complementary-Label Learning](https://mlsanity.com/paper/2411.12276/) (2024)

## Built on by (most cited first, 2 of 2)

- [Synthetic Swarm Mosquito Dataset for Acoustic Classification: A Proof of Concept](https://mlsanity.com/paper/2512.12365/) (2025)
- [Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes](https://mlsanity.com/paper/2605.15586/) (2026)

## Abstract (arXiv)

In this paper, we investigate the challenges of complementary-label learning (CLL), a specialized form of weakly-supervised learning (WSL) where models are trained with labels indicating classes to which instances do not belong, rather than standard ordinary labels. This alternative supervision is appealing because collecting complementary labels is generally cheaper and less labor-intensive. Although most existing research in CLL emphasizes the development of novel loss functions, the potential of data augmentation in this domain remains largely underexplored. In this work, we uncover that the widely-used Mixup data augmentation technique is ineffective when directly applied to CLL. Through in-depth analysis, we identify that the complementary-label noise generated by Mixup negatively impacts the performance of CLL models. We then propose an improved technique called Intra-Cluster Mixup (ICM), which only synthesizes augmented data from nearby examples, to mitigate the noise effect. ICM carries the benefits of encouraging complementary label sharing of nearby examples, and leads to substantial performance improvements across synthetic and real-world labeled datasets. In particular, our wide spectrum of experimental results on both balanced and imbalanced CLL settings justifies the potential of ICM in allying with state-of-the-art CLL algorithms, achieving significant accuracy increases of 30% and 10% on MNIST and CIFAR datasets, respectively.