Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Tianyi, Wang, Haobo, Tang, Kai, Lyu, Gengyu, Hu, Tianlei, Chen, Gang, Ma, Hong, Xiang, Meixiang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917417965322240
author Chen, Tianyi
Wang, Haobo
Tang, Kai
Lyu, Gengyu
Hu, Tianlei
Chen, Gang
Ma, Hong
Xiang, Meixiang
author_facet Chen, Tianyi
Wang, Haobo
Tang, Kai
Lyu, Gengyu
Hu, Tianlei
Chen, Gang
Ma, Hong
Xiang, Meixiang
contents 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 Poincaré 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16959
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering
Chen, Tianyi
Wang, Haobo
Tang, Kai
Lyu, Gengyu
Hu, Tianlei
Chen, Gang
Ma, Hong
Xiang, Meixiang
Machine Learning
Computer Vision and Pattern Recognition
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 Poincaré 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.
title Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.16959