We study the problem of learning a binary classifier on the vertices of a graph. In particular,
we consider classifiers given by\emph {monophonic halfspaces}, partitions of the vertices …

We systematically study the query complexity of learning geodesically convex halfspaces on
graphs. Geodesic convexity is a natural generalisation of Euclidean convexity and allows …

This paper investigates the problem of active learning for binary label prediction on a graph.
We introduce a simple and label-efficient algorithm called S^ 2 for this task. At each step, S …

We investigate methods for selecting sets of labeled vertices for use in predicting the labels
of vertices on a graph. We specifically study methods which choose a single batch of labeled …

We consider active, semi-supervised learning in an offline transductive setting. We show that
a previously proposed error bound for active learning on undirected weighted graphs can be …

We investigate the problem of active learning on a given tree whose nodes are assigned
binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we …

We investigate the problem of exact cluster recovery using oracle queries. Previous results
show that clusters in Euclidean spaces that are convex and separated with a margin can be …

We study active learning of multiclass classifiers, focusing on the realizable transductive
setting. The input is a finite subset $ X $ of some metric space, and the concept to be learned …

We study the problem of learning the clusters of a given graph in the self-directed learning
setup. This learning setting is a variant of online learning, where rather than an adversary …

We study the problem of classifying the nodes of a given graph in the self-directed learning
setup. This learning setting is a variant of online learning, where rather than an adversary …