Labeled diffusion-constrained nonnegative matrix factorization for multiview clustering

Key Points

• Clustering accuracy improves with labeled diffusion constraints, showing significant enhancement in data representation.
• An increase in clustering accuracy of up to 15% highlights the effectiveness of the approach.
• The proposed method for multiview clustering employs nonnegative matrix factorization with a novel labeling technique.
• Results imply a potential for better data representation in various applications involving complex datasets.