TitleCautious Collective Classification
Publication TypeJournal Article
Year of Publication2009
AuthorsMcDowell, LK, Gupta, KM, Aha, DW
JournalJournal of Machine Learning Research
Volume10
Pagination2777-2836
Date Published12/2009
Keywordsapproximate probabilistic inference, cautious inference, collective inference, networked data, statistical relational learning
Abstract

Many collective classification (CC) algorithms have been shown to increase accuracy when instances
are interrelated. However, CC algorithms must be carefully applied because their use of
estimated labels can in some cases decrease accuracy. In this article, we show that managing this
label uncertainty through cautious algorithmic behavior is essential to achieving maximal, robust
performance. First, we describe cautious inference and explain how four well-known families of
CC algorithms can be parameterized to use varying degrees of such caution. Second, we introduce
cautious learning and show how it can be used to improve the performance of almost any CC algorithm,
with or without cautious inference. We then evaluate cautious inference and learning for
the four collective inference families, with three local classifiers and a range of both synthetic and
real-world data. We find that cautious learning and cautious inference typically outperform less
cautious approaches. In addition, we identify the data characteristics that predict more substantial
performance differences. Our results reveal that the degree of caution used usually has a larger impact
on performance than the choice of the underlying inference algorithm. Together, these results
identify the most appropriate CC algorithms to use for particular task characteristics and explain
multiple conflicting findings from prior CC research.

Full Text
pdf: 
http://www.nrl.navy.mil/itd/aic/sites/www.nrl.navy.mil.itd.aic/files/pdfs/mcdowell09a.pdf
NRL Publication Release Number: 
09-1226-0864
pub_tags: 
machine learning
collective classification
cautious methods