Efficient Multi-View Graph Clustering with Local and Global Structure Preservation

TL;DR

This paper introduces EMVGC-LG, an efficient multi-view graph clustering method that preserves both local and global structures, improving clustering accuracy while maintaining linear scalability.

Contribution

The paper proposes a novel framework that jointly optimizes anchor construction and graph learning to incorporate local and global structural information in multi-view clustering.

Findings

Outperforms existing methods in clustering accuracy.

Maintains linear complexity with respect to data size.

Demonstrates effectiveness and efficiency through extensive experiments.

Abstract

Anchor-based multi-view graph clustering (AMVGC) has received abundant attention owing to its high efficiency and the capability to capture complementary structural information across multiple views. Intuitively, a high-quality anchor graph plays an essential role in the success of AMVGC. However, the existing AMVGC methods only consider single-structure information, i.e., local or global structure, which provides insufficient information for the learning task. To be specific, the over-scattered global structure leads to learned anchors failing to depict the cluster partition well. In contrast, the local structure with an improper similarity measure results in potentially inaccurate anchor assignment, ultimately leading to sub-optimal clustering performance. To tackle the issue, we propose a novel anchor-based multi-view graph clustering framework termed Efficient Multi-View Graph Clustering with Local and Global Structure Preservation (EMVGC-LG). Specifically, a unified framework with a theoretical guarantee is designed to capture local and global information. Besides, EMVGC-LG jointly optimizes anchor construction and graph learning to enhance the clustering quality. In addition, EMVGC-LG inherits the linear complexity of existing AMVGC methods respecting the sample number, which is time-economical and scales well with the data size. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method.