Graph Based Semi-supervised Learning with Sharper Edges

In many graph-based semi-supervised learning algorithms, edge weights are assumed to be fixed and determined by the data points' (often symmetric) relationships in input space, without considering directionality. However, relationships may be more informative in one direction (e.g. from labelled to unlabelled) than in the reverse direction, and some relationships (e.g. strong weights between oppositely labelled points) are unhelpful in either direction. Undesirable edges may reduce the amount of influence an informative point can propagate to its neighbours

• Type: Conference
• Year: 2006
• Where: ECML
• Authors: Hyunjung Shin, N. Jeremy Hill, Gunnar Rätsch
• Keywords: ECML 2006, Graph-based Semi-supervised Learning, Labelled Points, Machine Learning, Strong Weights