Online learning over graphs

We apply classic online learning techniques similar to the perceptron algorithm to the problem of learning a function defined on a graph. The benefit of our approach includes simple algorithms and performance guarantees that we naturally interpret in terms of structural properties of the graph, such as the algebraic connectivity or the diameter of the graph. We also discuss how these methods can be modified to allow active learning on a graph. We present preliminary experiments with encouraging results.

• Type: Conference
• Year: 2005
• Where: ICML
• Authors: Mark Herbster, Massimiliano Pontil, Lisa Wainer
• Keywords: Active Learning, Classic Online Learning, ICML 2005, Machine Learning, Perceptron Algorithm