Collective Classification
...
Page
Category
Word1
WordN
From-
...
Page
Category
Word1
WordN
Link
Exists
To-
[Getoor, Segal, Taskar, Koller]
Approx. inference: belief propagation
0
0.05
0.1
0.15
0.2
0.25
0.3
0.35
words only
link words
collective
Classify all pages collectively,
maximizing the joint label probability
A more interesting approach is based on the realization that this domain is relational.  It has objects that are linked to each other.  And the links are very meaningful in and of themselves.  For example, a student webpage is very likely to point to his advisor’s page.  But faculty rarely link to each other, neither do courses and researh projects.
Note that we can’t have an edge directly between categories of the pages – this will cause cycles in the bayes net.
However we can represent these trends by asserting that the existence of a link depends on the category of the two pages pointing to it. This allows us to use, for example, a webpage that we are fairly sure is a student page to give evidence about the fact that a page it points to is a faculty webpage.  In fact, they can both give evidence about each other, giving rise to a form of “collective classification”.