PML-MA restores feature-label consistency in partial multi-label learning by generating pseudo-labels via low-rank orthogonal decomposition, aligning modalities globally and locally, and using multi-peak prototypes for refinement.
First, we update the scalar weight matrixDusing the result of the current iteration round Rt: dt+1 ii = cX j=1 rt ij.(30) Then, the suboptimization problem forRderived from Eq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Feature-Label Modal Alignment for Robust Partial Multi-Label Learning
PML-MA restores feature-label consistency in partial multi-label learning by generating pseudo-labels via low-rank orthogonal decomposition, aligning modalities globally and locally, and using multi-peak prototypes for refinement.