PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Online Learning over Graphs
Mark Herbster, Massimiliano Pontil and Lisa Wainer
In: ICML 2005, Bonn, Germany(2005).

Abstract

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 fast algorithms and simple 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.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:997
Deposited By:Massimiliano Pontil
Deposited On:11 July 2005