We continue our study of online prediction of the labelling of a graph. We show a fundamental limitation of Laplacian-based algorithms: if the graph has a large diameter then the ...
We show that the mistake bound for predicting the nodes of an arbitrary weighted graph is characterized (up to logarithmic factors) by the cutsize of a random spanning tree of the...
Abstract. Graph programs as introduced by Habel and Plump [8] provide a simple yet computationally complete language for computing functions and relations on graphs. We extend this...
Abstract. We study the problem of learning partitions using equivalence constraints as input. This is a binary classification problem in the product space of pairs of datapoints. ...
Abstract--This paper presents a new, simple, and efficient segmentation approach, based on a fusion procedure which aims at combining several segmentation maps associated to simple...