Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

GCFAgg

GCFAgg, short for Global and Cross-View Feature Aggregation, is a deep representation learning framework designed for multi-view clustering to partition unlabeled data into categories by synthesizing information across multiple data perspectives. Unlike conventional approaches that aggregate features solely on a per-view basis and overlook broader relational context, GCFAgg generates a unified consensus representation by performing feature aggregation across both different views and multiple sample instances simultaneously. This enables the model to exploit complementary information while preserving the global structural relationships among similar data points. The approach typically incorporates structure-guided contrastive learning to align view-specific representations with the learned consensus representation, ensuring that samples sharing strong structural similarities remain close in the feature space, and it functions as a flexible module suitable for both complete and incomplete multi-view clustering tasks.

1 item

GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering

GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering

Weiqing Yan, Yuanyang Zhang, Chenlei Lv, Chang Tang, Guanghui Yue, Liang Liao, Weisi Lin

OrganizationsChina University of GeosciencesNanyang Technological UniversityShenzhen UniversityYantai University

Why you should read this

Proposes a global and cross-view feature aggregation framework that integrates transformer-based sample relationships with structure-guided contrastive learning to boost multi-view clustering performance on both complete and incomplete datasets.

Multi-view clustering can partition data samples into their categories by learning a consensus representation in unsupervised way and has received more and more attention in recent years. However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples. In this paper, we propose a novel multi-view clustering network to address these problems, called Global and Cross-view Feature Aggregation for Multi-View Clustering (GCFAggMVC). Specifically, the consensus data presentation from multiple views is obtained via cross-sample and cross-view feature aggregation, which fully explores the complementary of similar samples. Moreover, we align the consensus representation and the view-specific representation by the structure-guided contrastive learning module, which makes the view-specific representations from different samples with high structure relationship similar. The proposed module is a flexible multi-view data representation module, which can be also embedded to the incomplete multi-view data clustering task via plugging our module into other frameworks. Extensive experiments show that the proposed method achieves excellent performance in both complete multi-view data clustering tasks and incomplete multi-view data clustering tasks.

Added

2026-09-26