Tensor-based Graph Learning with Consistency and Specificity for Multi-view Clustering

2024-03-27

arXiv.org

AI Summary

To address two key challenges in multi-view clustering—(1) the inadequacy of Euclidean distance in capturing intrinsic high-dimensional data structure, and (2) imbalanced modeling of consensus and view-specific graphs with insufficient noise suppression—this paper proposes a tensor decomposition-based adaptive graph learning framework. Its core contributions are: (1) the first unified tensor representation jointly modeling consensus, specificity, and an explicit noise graph to enable clean component separation; (2) a novel similarity metric defined on the Stiefel manifold, replacing conventional Euclidean distance; and (3) robust graph fusion via truncated tensor singular value decomposition (t-SVD) integrated with manifold optimization. Extensive experiments on six benchmark datasets demonstrate significant improvements over state-of-the-art methods in both clustering accuracy and noise robustness. The source code is publicly available, confirming the framework’s dual advantages in performance and resilience.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

In the context of multi-view clustering, graph learning is recognized as a crucial technique, which generally involves constructing an adaptive neighbor graph based on probabilistic neighbors, and then learning a consensus graph to for clustering. However, they are confronted with two limitations. Firstly, they often rely on Euclidean distance to measure similarity when constructing the adaptive neighbor graph, which proves inadequate in capturing the intrinsic structure among data points in practice. Secondly, most of these methods focus solely on consensus graph, ignoring unique information from each view. Although a few graph-based studies have considered using specific information as well, the modelling approach employed does not exclude the noise impact from the specific component. To this end, we propose a novel tensor-based multi-view graph learning framework that simultaneously considers consistency and specificity, while effectively eliminating the influence of noise. Specifically, we calculate similarity distance on the Stiefel manifold to preserve the intrinsic properties of data. By making an assumption that the learned neighbor graph of each view comprises a consistent part, a specific part, and a noise part, we formulate a new tensor-based target graph learning paradigm for noise-free graph fusion. Owing to the benefits of tensor singular value decomposition (t-SVD) in uncovering high-order correlations, this model is capable of achieving a complete understanding of the target graph. Furthermore, we derive an algorithm to address the optimization problem. Experiments on six datasets have demonstrated the superiority of our method. We have released the source code on https://github.com/lshi91/CSTGL-Code.

Problem

• Improving graph learning for high-dimensional multi-view clustering
• Balancing consistency and specificity in multi-view graph fusion
• Eliminating noise impact in tensor-based graph learning

Innovation

• Tensor-based graph learning with consistency and specificity
• Pseudo-Stiefel manifold distance for similarity measurement
• Tensor SVD for noise-free high-order graph fusion