Efficient Label Propagation

65 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Transductive Multi-View Zero-Shot Learning (2015, background): “[19], where t is an iteration parameter in their paper and t nT .”
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, background): “Finally, the standard label propagation [72] gives the closed-form solution:”
An Overview of Deep Semi-Supervised Learning (2020, background): “In label propagation [189, 183, 46], the labeling scores are defined as the optimal solution that minimizes the loss function.”
Label Propagation via Teaching-to-Learn and Learning-to-Teach (2017, background): “Recently, some researchers adapted the traditional label propagation methods to large-scale scenarios via either efficient graph construction [11] or efficient labeling [12].”
Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning (2018, background): “On the other hand, there are plenty of prior work on the scalability and efficiency of label propagation, such as Liang and Li (2018); Fujiwara and Irie (2014), which can extend our work to large-scale data.”
Learning Transferable Knowledge Through Embedding Spaces (2019, background): “[77] proposed to iteratively compute lower and upper-bounds of labeling scores to avoid unnecessary score computation and”