Herbster, M.;
Pontil, M.;
Wainder, L.;
(2005)
Online learning over graphs.
In: Dzeroski, S. and De Raedt, L. and Wrobel, S., (eds.)
Proceedings of the 22nd International Conference on Machine Learning (ICML 05).
(pp. pp. 305-312).
ACM Press: New York, NY, USA.
![[thumbnail of gpercicmlfin.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/application_pdf.png) Preview |
PDF
gpercicmlfin.pdf Download (243kB) |
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 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: | Proceedings paper |
|---|---|
| Title: | Online learning over graphs |
| ISBN: | 1595931805 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/1102351.1102390 |
| Publisher version: | http://dx.doi.org/10.1145/1102351.1102390 |
| Language: | English |
| Additional information: | © ACM, 2005. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in the Proceedings of the 22nd International Conference on Machine learning (ICML 05) (2005) http://doi.acm.org/10.1145/1102351.1102390. Paper presented at the ACM International Conference Proceeding Series, Bonn, Germany, 7-11 August 2005 |
| URI: | https://discovery.ucl.ac.uk/id/eprint/13334 |
Archive Staff Only
 |
View Item |
