A Comprehensive Survey on Spectral Clustering with Graph Structure Learnin

2025-01-23

AI Summary

Spectral clustering often suffers from suboptimal performance and limited interpretability on high-dimensional, non-convex, and multi-view data due to reliance on predefined or poorly structured graphs. Method: This paper systematically analyzes Graph Structure Learning (GSL) in spectral clustering through a novel three-dimensional taxonomy—categorizing approaches by graph construction (fixed vs. adaptive), number of views (single vs. multi-view), and optimization strategy (one-step vs. two-step). It further synthesizes key techniques including pairwise similarity modeling, anchor-based graph learning, hypergraph construction, and feature- or decision-level fusion. Contribution/Results: The work establishes the first unified modeling framework for GSL in spectral clustering, constructs a knowledge graph illustrating the co-evolution of spectral clustering and GSL, and identifies three critical research directions—scalability, robustness, and theoretical consistency—providing a principled methodology for clustering large-scale, complex data.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

Spectral clustering is a powerful technique for clustering high-dimensional data, utilizing graph-based representations to detect complex, non-linear structures and non-convex clusters. The construction of a similarity graph is essential for ensuring accurate and effective clustering, making graph structure learning (GSL) central for enhancing spectral clustering performance in response to the growing demand for scalable solutions. Despite advancements in GSL, there is a lack of comprehensive surveys specifically addressing its role within spectral clustering. To bridge this gap, this survey presents a comprehensive review of spectral clustering methods, emphasizing on the critical role of GSL. We explore various graph construction techniques, including pairwise, anchor, and hypergraph-based methods, in both fixed and adaptive settings. Additionally, we categorize spectral clustering approaches into single-view and multi-view frameworks, examining their applications within one-step and two-step clustering processes. We also discuss multi-view information fusion techniques and their impact on clustering data. By addressing current challenges and proposing future research directions, this survey provides valuable insights for advancing spectral clustering methodologies and highlights the pivotal role of GSL in tackling large-scale and high-dimensional data clustering tasks.

Problem

• Spectral Clustering
• Graph Structure Learning
• Data Fusion

Innovation

• Spectral Clustering
• Graph Structure Learning (GSL)
• Multi-view Data Fusion