Learning Multi-View Representations with Graph-Level Fusion: A Bi-Level Optimization Perspective

doi:10.3390/bdcc10090289

Learning Multi-View Representations with Graph-Level Fusion: A Bi-Level Optimization Perspective

2026-08-28

0

OA

AI

DOI：10.3390/bdcc10090289

Original

Save

View PDF

Abstract

En 中文

Multi-view representation learning, aiming to extract discriminative patterns from heterogeneous data sources, has attracted increasing attention in recent years. A central challenge in multi-view data fusion lies in determining the appropriate weight and importance of each view in a principled manner. While graph-based methodologies have proven effective for multi-view learning, the systematic development of optimization-centric methodologies for consistent graph fusion remains in its nascent stages. Furthermore, the lack of explicit alignment between the latent feature representation space and the graph space is frequently overlooked, ultimately compromising the consistency of the shared representation. To this end, we propose a bi-level framework for joint multi-view feature representation learning and graph fusion, which formally formulates the multi-view data fusion task as a rigorous mathematical optimization problem. The proposed approach demonstrates consistent effectiveness in clustering tasks, achieving state-of-the-art performance on six benchmark datasets with accuracy improvements ranging up to 9.73 % over existing methods.

Keywords:

multi-view learning

bi-level optimization

multi-view clustering

graph fusion

graph neural network

manifold learning

Learning Multi-View Representations with Graph-Level Fusion: A Bi-Level Optimization Perspective

Abstract

AI Summary

Journal

Organization