Government of Canada
Symbol of the Government of Canada
 
 
 
 

Transductive relational classification in the co-training paradigm

 
 
Affiliation:
NRC Institute for Information Technology; National Research Council Canada
Language:
English
Type:
Conference publication
Conference:
8th International Conference on Machine Learning and Data Mining (MLDM) 2012, 13-20 July 2012 Berlin, Germany
Proceedings
Title:
Machine Learning and Data Mining in Pattern Recognition
Series:
Lecture Notes in Computer Science
Date:
2012
Pages :
11-25
NPArC #:
20494948
Keywords:
transductive learning; co-training; multi-relational classification
Program(s):
3D Imaging, Modeling and Visualization; Imagerie 3D, modélisation et visualisation
Group(s):
Visual Information Technology; Technologie de l'information visuelle
Abstract:
Consider a multi-relational database, to be used for classification, that contains a large number of unlabeled data. It follows that the cost of labeling such data is prohibitive. Transductive learning, which learns from labeled as well as from unlabeled data already known at learning time, is highly suited to address this scenario. In this paper, we construct multi-views from a relational database, by considering different subsets of the tables as contained in a multi-relational database. These views are used to boost the classification of examples in a co-training schema. The automatically generated views allow us to overcome the independence problem that negatively affect the performance of co-training methods. Our experimental evaluation empirically shows that co-training is beneficial in the transductive learning setting when mining multi-relational data and that our approach works well with only a small amount of labeled data.
 
Bookmark and Share:
 
 
 
 
Link:
HTML Link: