The cost of learning directed cuts
Thomas Gaertner and Gemma Garriga
In: ECML 2007, Oct 2007, Warsaw, Poland.
Abstract. In this paper we investigate the problem of classifying ver-
tices of a directed graph according to an unknown directed cut. We first
consider the usual setting in which the directed cut is fixed. However,
even in this setting learning is not possible without in the worst case
needing the labels for the whole vertex set. By considering the size of
the minimum path cover as a fixed parameter, we derive positive learn-
ability results with tight performance guarantees for active, online, as
well as PAC learning. The advantage of this parameter over possible al-
ternatives is that it allows for an a priori estimation of the total cost
of labelling all vertices. The main result of this paper is the analysis of
learning directed cuts that depend on a hidden and changing context.