Item

Abstract

Many real-world applications with graph data require the efficient solution of a given regression task as well as the identification of the subgraphs which are relevant for the task. In these cases graphs
are commonly represented as binary vectors of indicators of subgraphs, giving rise to an intractable input dimensionality.
An efficient solution to this problem was recently proposed by a Lasso-type
method where the objective function optimization over an intractable
number of variables is reformulated as a dual mathematical programming problem
over a small number of variables but a large number of constraints. The
dual problem is then solved by column generation where the subgraphs corresponding
to the most violated constraints are found by weighted subgraph mining.
This paper proposes an extension of this method to a fully Bayesian approach which
defines a prior distribution on the parameters and integrate them out from the model, thus providing a posterior distribution on the target variable as
opposed to a single estimate. The advantage of this approach is that
the extra information given by the target posterior distribution can be used for improving
the model in several ways. In this paper, we use the target posterior variance as a measure of uncertainty in the
prediction and show that, by rejecting unconfident predictions, we can improve state-of-the-art
performance on several molecular graph datasets.