# Multi-View Intact Space Learning

arXiv: https://arxiv.org/abs/1904.02340 · HTML: https://mlsanity.com/paper/1904.02340/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 11 of 11)

- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Heterogeneous Contrastive Learning](https://mlsanity.com/paper/2105.09401/) (2021)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [Adaptively-weighted Integral Space for Fast Multiview Clustering](https://mlsanity.com/paper/2208.12808/) (2022)
- [Multi-view Data Visualisation via Manifold Learning](https://mlsanity.com/paper/2101.06763/) (2021)
- [Cross-Modal and Multimodal Data Analysis Based on Functional Mapping of Spectral Descriptors and Manifold Regularization](https://mlsanity.com/paper/2105.05631/) (2021)
- [Error Loss Networks](https://mlsanity.com/paper/2106.03722/) (2021)
- [Attentive Multi-View Deep Subspace Clustering Net](https://mlsanity.com/paper/2112.12506/) (2021)
- [Locality Relationship Constrained Multi-view Clustering Framework](https://mlsanity.com/paper/2107.05073/) (2021)
- [Double Graphs Regularized Multi-view Subspace Clustering](https://mlsanity.com/paper/2209.15143/) (2022)
- [SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering](https://mlsanity.com/paper/2607.10413/) (2026)

## Abstract (arXiv)

It is practical to assume that an individual view is unlikely to be sufficient for effective multi-view learning. Therefore, integration of multi-view information is both valuable and necessary. In this paper, we propose the Multi-view Intact Space Learning (MISL) algorithm, which integrates the encoded complementary information in multiple views to discover a latent intact representation of the data. Even though each view on its own is insufficient, we show theoretically that by combing multiple views we can obtain abundant information for latent intact space learning. Employing the Cauchy loss (a technique used in statistical learning) as the error measurement strengthens robustness to outliers. We propose a new definition of multi-view stability and then derive the generalization error bound based on multi-view stability and Rademacher complexity, and show that the complementarity between multiple views is beneficial for the stability and generalization. MISL is efficiently optimized using a novel Iteratively Reweight Residuals (IRR) technique, whose convergence is theoretically analyzed. Experiments on synthetic data and real-world datasets demonstrate that MISL is an effective and promising algorithm for practical applications.