home › event - an analysis of how ensembles of collective classifiers improve predictions in graphs

EVENT:

An Analysis of How Ensembles of Collective Classifiers Improve Predictions in Graphs
Conferences & Talks

The 21st ACM International Conference on Information and Knowledge Management (CIKM 2012)

29 October 2012
1:30-3:35pm
Sheraton Maui, Maui, Hawaii

 

description

We present a theoretical analysis framework that shows how ensembles of collective classifiers can improve predictions for graph data. We show how collective ensemble classification reduces errors due to variance in learning and more interestingly inference. We also present an empirical framework that includes various ensemble techniques for classifying relational data using collective inference. The methods span single- and multiple-graph network approaches, and are tested on both synthetic and real world classification tasks. Our experimental results, supported by our theoretical justifications, confirm that ensemble algorithms that explicitly focus on both learning and inference processes and aim at reducing errors associated with both, are the best performers.

 

upcoming events   view all 

Joshua Wolf Shenk: The Power of Two
6 October 2014
Conferences & Talks  

Leadership and Tactics for Creating Digital Disruption
John Rossman
16 October 2014 | George E. Pake Auditorium, PARC
PARC Forum  

Automated Data Integration
Eric Huang, Author, Saigopal Nelaturi
27 October 2014
Conferences & Talks  

Global Competitiveness: The Role of Innovation and Productivity
Stephen Hoover, CEO, PARC
27 October 2014 | Toronto, Canada
Conferences & Talks  

The Internet of Everything
Stephen Hoover, CEO, PARC
28 October 2014 | Toronto, Canada
Conferences & Talks