.png){kind=icon}
.png){kind=icon}
Return
Information-Driven Complementarity and Consistency Mining for Multi-View Clustering
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2025.3639380.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-view clustering (MVC) has attracted considerable attention in the signal processing field. However, two issues still remain: 1) They adopt the concatenation or weighted combination as the fusion strategies, which makes it difficult to ensure semantic robustness of fusion representations. 2) They suffer from dominant view dependency that models over-rely on views with stronger clustering signals and neglect weaker views. Therefore, an information-driven complementarity and consistency mining method (ICCM) is devised for multi-view clustering. Specifically, ICCM designs view-specific representation learning and cluster partitioning module to extract inherent information in each view. Then, ICCM introduces an entropy-oriented complementary aggregation module to learn semantics-robust fusion representations through inter-view nonlinear transformations. Meanwhile, it proposes an invariance-driven consistent partition module to capture consistent cluster assignments across views where an adaptive weighting strategy is introduced to balance contributions of each view via assigning greater weights to views with fuzzy structures. Finally, experiments on six datasets demonstrate that ICCM gains cutting-edge results in MVC.
Keywords:
Multi-view data mining
entropy-oriented complementary aggregation
invariance-driven consistent partition
Journal
I
IF:
3.9
Papers:
600
Citations:
0