transductive-learning

This paper resolves the minimax rate for agnostic multiclass transductive learning, demonstrating that the optimal excess error is governed by the DS and Natarajan dimensions. The result holds for arbitrary label spaces, extending prior work on binary classification.

This paper introduces the Level-Constrained-Littlestone-Littlestone (LCLL) tree to characterize learnability in universal transductive online classification with possibly unbounded label spaces, proving that optimal mistake rates are either bounded or logarithmic.

This paper introduces Transductive Sharpening (TS), a loss-level modification for semi-supervised node classification that minimizes prediction entropy on unlabeled nodes while counterbalancing on labeled nodes, achieving consistent performance improvements without architectural changes.