COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction

By Yijie Lin, Yuanbiao Gou, Zitao Liu, Boyun Li, Jiancheng Lv, Xi Peng. Computer Vision and Pattern Recognition, 2021

440 citations recorded by the source corpus.

In this paper, we study two challenging problems in incomplete multi-view clustering analysis, namely, i) how to learn an informative and consistent representation among different views without the help of labels and ii) how to recover the missing views from data. To this end, we propose a novel objective that incorporates representation learning and data recovery into a unified framework from the view of information theory. To be specific, the informative and consistent representation is learned by maximizing the mutual information across different views through contrastive learning, and the missing views are recovered by minimizing the conditional entropy of different views through dual prediction. To the best of our knowledge, this could be the first work to provide a theoretical framework that unifies the consistent representation learning and cross-view data recovery. Extensive experimental results show the proposed method remarkably outperforms 10 competitive multi-view clustering methods on four challenging datasets. The code is available at https://pengxi.me.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f27eb4628711d1d4230e2ce285c1e658e9487798

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiancheng Lv
2. Joey Tianyi Zhou
3. Zongbo Han
4. Changqing Zhang
5. Zhao Kang
6. Yuanbiao Gou
7. Huan Fu
8. Jinfeng Bai

In Computer Vision and Pattern Recognition

1. Changqing Zhang
2. Huan Fu
3. Jiancheng Lv
4. Joey Tianyi Zhou
5. Zongbo Han
6. Liang Peng
7. Zhao Kang
8. Yuanbiao Gou

In Media Technology

1. Joey Tianyi Zhou
2. Changqing Zhang
3. Zhao Kang
4. Yuanbiao Gou
5. Huan Fu
6. Jiancheng Lv
7. Erlin Pan
8. Xiaocui Peng

Citations in the corpus

• Dual Contrastive Prediction for Incomplete Multi-View Representation Learning (2022, methodology): “First, most of the methods including [30] lack a theoretical understanding of the success of the learned representation, whereas we prove that DCP could learn a sufficient and minimal representation.”
• Multi-view Contrastive Graph Clustering (2021, positive): “Recently, by combining reconstruction, cross-view contrastive learning, and cross-view dual prediction, incomplete multi-view clustering via contrastive prediction (COMPLETER) [Lin et al., 2021a] performs data recovery and consistency learning of incomplete multi-view data simultaneously.”
• Multi-level Feature Learning for Contrastive Multi-view Clustering (2021, positive): “(2) Some MVC methods ( e.g ., [18, 21]) leverage the consistency objective on the latent features to explore the common semantics across all views.”
• Trusted Multi-View Classification With Dynamic Evidential Fusion (2022, methodology): “These methods are typically built on complex models [1], [2], [3], [4], [5], [6], [7] (usually integrating differ-”