# On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering

arXiv: https://arxiv.org/abs/2303.09877 · HTML: https://mlsanity.com/paper/2303.09877/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Reconsidering Representation Alignment for Multi-view Clustering](https://mlsanity.com/paper/2103.07738/) (2021)
- [Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering](https://mlsanity.com/paper/2106.11232/) (2021)
- [Deep Multimodal Subspace Clustering Networks](https://mlsanity.com/paper/1804.06498/) (2018)
- [Deep Embedded Multi-view Clustering with Collaborative Training](https://mlsanity.com/paper/2007.13067/) (2020)
- [Multi-view Deep Subspace Clustering Networks](https://mlsanity.com/paper/1908.01978/) (2019)
- [Shared Generative Latent Representation Learning for Multi-view Clustering](https://mlsanity.com/paper/1907.09747/) (2019)
- [Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering](https://mlsanity.com/paper/2204.12496/) (2022)
- [Deep Divergence-Based Approach to Clustering](https://mlsanity.com/paper/1902.04981/) (2019)
- [Guided Co-training for Large-Scale Multi-View Spectral Clustering](https://mlsanity.com/paper/1707.09866/) (2017)

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

- [Decoupled Contrastive Multi-View Clustering with High-Order Random Walks](https://mlsanity.com/paper/2308.11164/) (2023)
- [PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering](https://mlsanity.com/paper/2506.12408/) (2025)
- [Learning Disentangled Representations for Generalized Multi-view Clustering](https://mlsanity.com/paper/2605.15640/) (2026)
- [Deep Contrastive Multi-view Clustering under Semantic Feature Guidance](https://mlsanity.com/paper/2403.05768/) (2024)
- [Generalizable and Robust Spectral Method for Multi-view Representation Learning](https://mlsanity.com/paper/2411.02138/) (2024)
- [Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection](https://mlsanity.com/paper/2409.14882/) (2024)
- [Balanced Multi-view Clustering](https://mlsanity.com/paper/2501.02564/) (2025)
- [Mask-informed Deep Contrastive Incomplete Multi-view Clustering](https://mlsanity.com/paper/2502.02234/) (2025)
- [MCFCN: Multi-View Clustering via a Fusion-Consensus Graph Convolutional Network](https://mlsanity.com/paper/2511.05554/) (2025)
- [SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering](https://mlsanity.com/paper/2607.10413/) (2026)

## Abstract (arXiv)

Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of self-supervision-based methods for deep MVC, potentially slowing the progress of the field. To address this, we present DeepMVC, a unified framework for deep MVC that includes many recent methods as instances. We leverage our framework to make key observations about the effect of self-supervision, and in particular, drawbacks of aligning representations with contrastive learning. Further, we prove that contrastive alignment can negatively influence cluster separability, and that this effect becomes worse when the number of views increases. Motivated by our findings, we develop several new DeepMVC instances with new forms of self-supervision. We conduct extensive experiments and find that (i) in line with our theoretical findings, contrastive alignments decreases performance on datasets with many views; (ii) all methods benefit from some form of self-supervision; and (iii) our new instances outperform previous methods on several datasets. Based on our results, we suggest several promising directions for future research. To enhance the openness of the field, we provide an open-source implementation of DeepMVC, including recent models and our new instances. Our implementation includes a consistent evaluation protocol, facilitating fair and accurate evaluation of methods and components.