Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation

ArXi:2604.04170v1 Announce Type: cross Although multi-view multi-label learning has been extensively studied, research on the dual-missing scenario, where both views and labels are incomplete, remains largely unexplored. Existing methods mainly rely on contrastive learning or information bottleneck theory to learn consistent representations under missing-view conditions, but loss-based alignment without explicit structural constraints limits the ability to capture stable and discriminative shared semantics. To address this issue, we.