Wasserstein-Aligned Hyperbolic Multi-View Clustering

2025-12-10

AI Summary

To address semantic inconsistency across views and insufficient hierarchical structure modeling in multi-view clustering (MVC), this paper proposes a novel hyperbolic geometry-based MVC method. First, we design view-specific Lorentz manifold hypersphere encoders to explicitly capture hierarchical semantics. Second, we introduce the sliced Wasserstein distance—defined in hyperbolic space—for the first time in MVC to achieve global manifold distribution alignment, jointly enforcing instance-level correspondence and semantic consistency. Third, we tightly couple view-specific encoding with soft cluster assignment within an end-to-end jointly optimized framework. Extensive experiments on multiple benchmark datasets demonstrate state-of-the-art performance, with significant improvements in robustness against noise and inter-view heterogeneity. The method effectively leverages the intrinsic hierarchical and tree-like properties of hyperbolic geometry to better model semantic relationships across diverse views.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• 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: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Multi-view clustering (MVC) aims to uncover the latent structure of multi-view data by learning view-common and view-specific information. Although recent studies have explored hyperbolic representations for better tackling the representation gap between different views, they focus primarily on instance-level alignment and neglect global semantic consistency, rendering them vulnerable to view-specific information ( extit{e.g.}, noise and cross-view discrepancies). To this end, this paper proposes a novel Wasserstein-Aligned Hyperbolic (WAH) framework for multi-view clustering. Specifically, our method exploits a view-specific hyperbolic encoder for each view to embed features into the Lorentz manifold for hierarchical semantic modeling. Whereafter, a global semantic loss based on the hyperbolic sliced-Wasserstein distance is introduced to align manifold distributions across views. This is followed by soft cluster assignments to encourage cross-view semantic consistency. Extensive experiments on multiple benchmarking datasets show that our method can achieve SOTA clustering performance.

Problem

• Aligns hyperbolic manifold distributions across views
• Enhances global semantic consistency in clustering
• Reduces vulnerability to view-specific noise and discrepancies

Innovation

• Hyperbolic encoders embed features into Lorentz manifold
• Sliced-Wasserstein distance aligns manifold distributions across views
• Soft cluster assignments enhance cross-view semantic consistency