Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering

arXiv:2604.16959v1 Announce Type: cross Abstract: Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining robustness against missing views. However, prevalent Euclidean-based methods suffer from a geometric mismatch when modeling real-world data with intrinsic hierarchies, leading to semantic blurring where representations drift towards spatially proximal but semantically distinct neighbors. To bridge this gap, we propose HERL, a Hyperbolic Enhanced Representation Learning framework for IMVC. Operating within the Poincare ball, HERL constructs a structure-aware latent space to enhance representation learning. Specifically, we design a dual-constraint hyperbolic contrastive mechanism optimizing: an angular-based loss to preserve semantic identity via directional alignment, and a distance-based loss to enforce hierarchical compactness. Furthermore, a hyperbolic prototype head is introduced to rectify global structural drift by aligning cross-view hierarchy-aware prototype distributions. Consequently, HERL disentangles fine-grained semantic correlations to sharpen cluster boundaries and imposes geometric constraints to rectify the data recovery process. Extensive experimental results demonstrate that HERL consistently outperforms state-of-the-art approaches.

Related

• Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder
• DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning
• Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregation
• Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale

Source: arXiv cs.CV | 2026-04-21