Deep multi-view clustering based on instance-level adaptive structural contrastive learning

Zengbiao Yang

doi:10.1016/j.neunet.2026.108581

Deep multi-view clustering based on instance-level adaptive structural contrastive learning

2026-01-09

0

PRE

AI

DOI：10.1016/j.neunet.2026.108581

Original

Original request for help

Save

Abstract

En 中文

• We propose an instance-level adaptive structural contrastive loss to enforce the consistency of clustering structures between the fused and individual view. • We propose incorporating global consistency clustering information when constructing adjacency matrices for individual views and the fused view, enhancing the attention to global structural consistency information during contrastive learning. • We propose constructing local and global consistency clustering information based on discovering clues and evaluating their consistency.

Deep multi-view clustering based on instance-level adaptive structural contrastive learning

Abstract

Journal

Organization