Deep Transfer via Second-Order Markov Logic
Jesse Davis
and
Pedro Domingos
Abstract:
Standard inductive learning requires that training and test instances
come from the same distribution. Transfer learning seeks to remove
this restriction. In shallow transfer, test instances are from the
same domain, but have a different distribution. In deep transfer, test
instances are from a different domain entirely (i.e., described by
different predicates). Humans routinely perform deep transfer, but
few learning systems, if any, are capable of it. In this paper we
propose an approach based on a form of second-order Markov logic. Our
algorithm discovers structural regularities in the source domain in
the form of Markov logic formulas with predicate variables, and
instantiates these formulas with predicates from the target
domain. Using this approach, we have successfully transferred learned
knowledge among molecular biology, social network and Web
domains. The discovered patterns include broadly useful properties of
predicates, like symmetry and transitivity, and relations among
predicates, such as various forms of homophily.
Download:
Paper (PDF)
Datasets used:
WebKB
Online Appendix
results