# Efficient and Effective Deep Multi-view Subspace Clustering

arXiv: https://arxiv.org/abs/2310.09718 · HTML: https://mlsanity.com/paper/2310.09718/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 15 Oct 2023.

## Builds on (most cited first, 20 of 20)

- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction](https://mlsanity.com/paper/2006.08558/) (2020)
- [Deep Subspace Clustering Networks](https://mlsanity.com/paper/1709.02508/) (2017)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [Large-scale Multi-view Subspace Clustering in Linear Time](https://mlsanity.com/paper/1911.09290/) (2019)
- [Robust and Efficient Subspace Segmentation via Least Squares Regression](https://mlsanity.com/paper/1404.6736/) (2014)
- [Self-Supervised Discriminative Feature Learning for Deep Multi-View Clustering](https://mlsanity.com/paper/2103.15069/) (2021)
- [Deep Multimodal Subspace Clustering Networks](https://mlsanity.com/paper/1804.06498/) (2018)
- [Learning a Self-Expressive Network for Subspace Clustering](https://mlsanity.com/paper/2110.04318/) (2021)
- [Auto-weighted Multi-view Clustering for Large-scale Data](https://mlsanity.com/paper/2303.01983/) (2023)
- [Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering](https://mlsanity.com/paper/2204.12496/) (2022)
- [Feature Concatenation Multi-view Subspace Clustering](https://mlsanity.com/paper/1901.10657/) (2019)
- [MetaViewer: Towards A Unified Multi-View Representation](https://mlsanity.com/paper/2303.06329/) (2023)
- [Multi-view Semantic Consistency based Information Bottleneck for Clustering](https://mlsanity.com/paper/2303.00002/) (2023)
- [Semantically Consistent Multi-view Representation Learning](https://mlsanity.com/paper/2303.04366/) (2023)
- [Unsupervised Deep Discriminant Analysis Based Clustering](https://mlsanity.com/paper/2206.04686/) (2022)
- [Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering](https://mlsanity.com/paper/2009.12875/) (2020)
- [Attentive Multi-View Deep Subspace Clustering Net](https://mlsanity.com/paper/2112.12506/) (2021)
- [Multi-View Clustering from the Perspective of Mutual Information](https://mlsanity.com/paper/2302.08743/) (2023)

## Abstract (arXiv)

Recent multi-view subspace clustering achieves impressive results utilizing deep networks, where the self-expressive correlation is typically modeled by a fully connected (FC) layer. However, they still suffer from two limitations. i) The parameter scale of the FC layer is quadratic to sample numbers, resulting in high time and memory costs that significantly degrade their feasibility in large-scale datasets. ii) It is under-explored to extract a unified representation that simultaneously satisfies minimal sufficiency and discriminability. To this end, we propose a novel deep framework, termed Efficient and Effective deep Multi-View Subspace Clustering (E2MVSC). Instead of a parameterized FC layer, we design a Relation-Metric Net that decouples network parameter scale from sample numbers for greater computational efficiency. Most importantly, the proposed method devises a multi-type auto-encoder to explicitly decouple consistent, complementary, and superfluous information from every view, which is supervised by a soft clustering assignment similarity constraint. Following information bottleneck theory and the maximal coding rate reduction principle, a sufficient yet minimal unified representation can be obtained, as well as pursuing intra-cluster aggregation and inter-cluster separability within it. Extensive experiments show that E2MVSC yields comparable results to existing methods and achieves state-of-the-art performance in various types of multi-view datasets.