Fast multiple graphs learning for multi-view clustering.

Area of Science:

• Computer Science
• Data Science
• Machine Learning

Background:

• Graph-based multi-view clustering is crucial for multimedia data analysis.
• Existing methods struggle with scalability and exploiting complementary information across views.

Purpose of the Study:

• To develop an efficient multi-view clustering model addressing scalability and information exploitation challenges.
• To propose a novel method utilizing anchor points and tensor Schatten p-norm minimization.

Main Methods:

• Constructing a tractable large graph using anchor graphs for each view.
• Employing tensor Schatten p-norm regularization to exploit complementary information.
• Developing a linear-time algorithm for efficient model solving.

Main Results:

• The proposed method demonstrates superior performance compared to state-of-the-art algorithms.
• Experimental results validate the effectiveness on various datasets.
• The approach successfully tackles scalability issues in large-scale graph learning.

Conclusions:

• The novel model efficiently handles large-scale multi-view clustering.
• It effectively leverages complementary information and spatial structures across views.
• The proposed method offers a scalable and effective solution for multi-view clustering problems.