TPCH: Tensor-interacted Projection and Cooperative Hashing for Multi-view Clustering

2024-12-25

AI Summary

To address the neglect of inter-view interactions and higher-order synergies in multi-view clustering projection, this paper proposes a tensorized joint projection and collaborative hashing framework. Methodologically, it pioneers stacking multi-view projection matrices into a third-order tensor and introduces an enhanced tensor nuclear norm to jointly model both cross-view and intra-view higher-order correlations. Furthermore, it jointly optimizes two-stage projections and collaborative hash functions within Hamming space. The resulting binary codes are compact, discriminative, and highly robust. Extensive experiments on five large-scale multi-view benchmarks demonstrate that the method significantly outperforms state-of-the-art approaches, achieving average improvements of 3.2–7.8 percentage points in clustering accuracy while reducing CPU runtime by over 40%.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

In recent years, anchor and hash-based multi-view clustering methods have gained attention for their efficiency and simplicity in handling large-scale data. However, existing methods often overlook the interactions among multi-view data and higher-order cooperative relationships during projection, negatively impacting the quality of hash representation in low-dimensional spaces, clustering performance, and sensitivity to noise. To address this issue, we propose a novel approach named Tensor-Interacted Projection and Cooperative Hashing for Multi-View Clustering(TPCH). TPCH stacks multiple projection matrices into a tensor, taking into account the synergies and communications during the projection process. By capturing higher-order multi-view information through dual projection and Hamming space, TPCH employs an enhanced tensor nuclear norm to learn more compact and distinguishable hash representations, promoting communication within and between views. Experimental results demonstrate that this refined method significantly outperforms state-of-the-art methods in clustering on five large-scale multi-view datasets. Moreover, in terms of CPU time, TPCH achieves substantial acceleration compared to the most advanced current methods. The code is available at extcolor{red}{url{https://github.com/jankin-wang/TPCH}}.

Problem

• Multi-perspective Data Classification
• Inter-perspective Correlation
• Deep-level Collaboration

Innovation

• Tensor Interaction Projection
• Collaborative Hashing
• Multi-perspective Data Classification