SEHFS: Structural Entropy-Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection
SEHFS addresses challenges in multi-view multi-label learning by using structural entropy to learn high-order feature correlations, which existing methods miss. It converts feature graphs into an encoding tree to group highly redundant features and introduces a framework fusing information theory and matrix methods to reconstruct a global view matrix, balancing local and global optimization for superior feature selection.