Abstract
This lecture overviews Label Propagation that has many applications in pattern recognition (semi-supervised learning) and in the study of diffusion processes. It covers the following topics in detail: Graph construction approaches (Adjacency Matrix Construction, Graph Weighting, Simultaneous Graph Construction and Weighting). Label Inference Methods (Graph Min-cut, Markov Random Fields, Gaussian Random Fields, Local and Global Consistency, Label Propagation on Data with Multiple Representations, Label Propagation on Hypergraphs). Label Propagation for Deep Learning.
Semi-supervised learning.
Label propagation for deep semi-supervised learning.
Label-Propgation-v1.1