TY - JOUR
T1 - Cross-View Approximation on Grassmann Manifold for Multiview Clustering
AU - Ma, Yidan
AU - Shen, Xinjie
AU - Wu, Danyang
AU - Cao, Jianfu
AU - Nie, Feiping
N1 - Publisher Copyright:
© 2012 IEEE.
PY - 2025
Y1 - 2025
N2 - In existing multiview clustering research, the comprehensive learning from multiview graph and feature spaces simultaneously remains insufficient when achieving a consistent clustering structure. In addition, a postprocessing step is often required. In light of these considerations, a cross-view approximation on Grassman manifold (CAGM) model is proposed to address inconsistencies within multiview adjacency matrices, feature matrices, and cross-view combinations from the two sources. The model uses a ratio-formed objective function, enabling parameter-free bidirectional fusion. Furthermore, the CAGM model incorporates a paired encoding mechanism to generate low-dimensional and orthogonal cross-view embeddings. Through the approximation of two measurable subspaces on the Grassmann manifold, the direct acquisition of the indicator matrix is realized. Furthermore, an effective optimization algorithm corresponding to the CAGM model is derived. Comprehensive experiments on four real-world datasets are conducted to substantiate the effectiveness of our proposed method.
AB - In existing multiview clustering research, the comprehensive learning from multiview graph and feature spaces simultaneously remains insufficient when achieving a consistent clustering structure. In addition, a postprocessing step is often required. In light of these considerations, a cross-view approximation on Grassman manifold (CAGM) model is proposed to address inconsistencies within multiview adjacency matrices, feature matrices, and cross-view combinations from the two sources. The model uses a ratio-formed objective function, enabling parameter-free bidirectional fusion. Furthermore, the CAGM model incorporates a paired encoding mechanism to generate low-dimensional and orthogonal cross-view embeddings. Through the approximation of two measurable subspaces on the Grassmann manifold, the direct acquisition of the indicator matrix is realized. Furthermore, an effective optimization algorithm corresponding to the CAGM model is derived. Comprehensive experiments on four real-world datasets are conducted to substantiate the effectiveness of our proposed method.
KW - Adaptively weighted learning
KW - Grassmann manifold
KW - bidirectional fusion
KW - multiview clustering
UR - http://www.scopus.com/inward/record.url?scp=105002289744&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2024.3388192
DO - 10.1109/TNNLS.2024.3388192
M3 - 文章
AN - SCOPUS:105002289744
SN - 2162-237X
VL - 36
SP - 7772
EP - 7777
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 4
ER -