# ConstraintMatch for Semi-constrained Clustering

arXiv: https://arxiv.org/abs/2311.15395 · HTML: https://mlsanity.com/paper/2311.15395/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 26 Nov 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Multi-class Classification without Multi-class Labels](https://mlsanity.com/paper/1901.00544/) (2019)
- [Deep Comprehensive Correlation Mining for Image Clustering](https://mlsanity.com/paper/1904.06925/) (2019)
- [FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.08505/) (2020)
- [MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering](https://mlsanity.com/paper/2105.01899/) (2021)
- [Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing](https://mlsanity.com/paper/2005.00820/) (2020)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders](https://mlsanity.com/paper/1703.07980/) (2017)
- [Neural network-based clustering using pairwise constraints](https://mlsanity.com/paper/1511.06321/) (2015)
- [A Framework for Deep Constrained Clustering](https://mlsanity.com/paper/2101.02792/) (2021)
- [Analysing the Noise Model Error for Realistic Noisy Label Data](https://mlsanity.com/paper/2101.09763/) (2021)
- [Clustering-driven Deep Embedding with Pairwise Constraints](https://mlsanity.com/paper/1803.08457/) (2018)
- [A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints](https://mlsanity.com/paper/2001.06720/) (2020)
- [Semi-Supervised Clustering with Neural Networks](https://mlsanity.com/paper/1806.01547/) (2018)

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

- [Angular Constraint Embedding via SpherePair Loss for Constrained Clustering](https://mlsanity.com/paper/2510.06907/) (2025)
- [Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision](https://mlsanity.com/paper/2608.12027/) (2026)

## Abstract (arXiv)

Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervision-level model performance. While they perform well even in the absence of the true underlying class labels, constrained clustering models still require large amounts of binary constraint annotations for training. In this paper, we propose a semi-supervised context whereby a large amount of textitunconstrained data is available alongside a smaller set of constraints, and propose textitConstraintMatch to leverage such unconstrained data. While a great deal of progress has been made in semi-supervised learning using full labels, there are a number of challenges that prevent a naive application of the resulting methods in the constraint-based label setting. Therefore, we reason about and analyze these challenges, specifically 1) proposing a textitpseudo-constraining mechanism to overcome the confirmation bias, a major weakness of pseudo-labeling, 2) developing new methods for pseudo-labeling towards the selection of textitinformative unconstrained samples, 3) showing that this also allows the use of pairwise loss functions for the initial and auxiliary losses which facilitates semi-constrained model training. In extensive experiments, we demonstrate the effectiveness of ConstraintMatch over relevant baselines in both the regular clustering and overclustering scenarios on five challenging benchmarks and provide analyses of its several components.