# Preventing Dimensional Collapse of Incomplete Multi-View Clustering via Direct Contrastive Learning

arXiv: https://arxiv.org/abs/2303.12241 · HTML: https://mlsanity.com/paper/2303.12241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 66 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [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)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss](https://mlsanity.com/paper/2106.04156/) (2021)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [Doubly Aligned Incomplete Multi-view Clustering](https://mlsanity.com/paper/1903.02785/) (2019)
- [DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network](https://mlsanity.com/paper/2103.07893/) (2021)
- [Semantically Contrastive Learning for Low-light Image Enhancement](https://mlsanity.com/paper/2112.06451/) (2021)
- [Generative Partial Multi-View Clustering](https://mlsanity.com/paper/2003.13088/) (2020)
- [One-Pass Incomplete Multi-view Clustering](https://mlsanity.com/paper/1903.00637/) (2019)
- [Spectral Perturbation Meets Incomplete Multi-view Data](https://mlsanity.com/paper/1906.00098/) (2019)
- [Incomplete Multi-view Clustering via Graph Regularized Matrix Factorization](https://mlsanity.com/paper/1809.05998/) (2018)
- [Clustering on Multiple Incomplete Datasets via Collective Kernel Learning](https://mlsanity.com/paper/1310.1177/) (2013)

## Abstract (arXiv)

Incomplete multi-view clustering (IMVC) is an unsupervised approach, among which IMVC via contrastive learning has received attention due to its excellent performance. The previous methods have the following problems: 1) Over-reliance on additional projection heads when solving the dimensional collapse problem in which latent features are only valid in lower-dimensional subspaces during clustering. However, many parameters in the projection heads are unnecessary. 2) The recovered view contain inconsistent private information and useless private information will mislead the learning of common semantics due to consistent learning and reconstruction learning on the same feature. To address the above issues, we propose a novel incomplete multi-view contrastive clustering framework. This framework directly optimizes the latent feature subspace, utilizes the learned feature vectors and their sub-vectors for reconstruction learning and consistency learning, thereby effectively avoiding dimensional collapse without relying on projection heads. Since reconstruction loss and contrastive loss are performed on different features, the adverse effect of useless private information is reduced. For the incomplete data, the missing information is recovered by the cross-view prediction mechanism and the inconsistent information from different views is discarded by the minimum conditional entropy to further avoid the influence of private information. Extensive experimental results of the method on 5 public datasets show that the method achieves state-of-the-art clustering results.