A Comparative Study of Distributional and Symbolic Paradigms
for Relational Learning
Abstract
Many real-world domains can be expressed as
graphs and, more generally, as multi-relational
knowledge graphs. Though reasoning and learning
with knowledge graphs has traditionally been addressed by symbolic approaches such as Statistical
relational learning, recent methods in (deep) representation learning have shown promising results
for specialised tasks such as knowledge base completion. These approaches, also known as distributional, abandon the traditional symbolic paradigm
by replacing symbols with vectors in Euclidean
space. With few exceptions, symbolic and distributional approaches are explored in different communities and little is known about their respective
strengths and weaknesses. In this work, we compare distributional and symbolic relational learning
approaches on various standard relational classifi-
cation and knowledge base completion tasks. Furthermore, we analyse the complexity of the rules
used implicitly by these approaches and relate them
to the performance of the methods in the comparison. The results reveal possible indicators that
could help in choosing one approach over the other
for particular knowledge graphs