Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
Normalize Then Propagate: Efficient Homophilous Regularization for Few-shot Semi-Supervised Node Classification
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
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.