DeepAI AI Chat
Log In Sign Up

Random Spanning Trees and the Prediction of Weighted Graphs

by   Nicolò Cesa-Bianchi, et al.
Università degli Studi di Milano

We investigate the problem of sequentially predicting the binary labels on the nodes of an arbitrary weighted graph. We show that, under a suitable parametrization of the problem, the optimal number of prediction mistakes can be characterized (up to logarithmic factors) by the cutsize of a random spanning tree of the graph. The cutsize is induced by the unknown adversarial labeling of the graph nodes. In deriving our characterization, we obtain a simple randomized algorithm achieving in expectation the optimal mistake bound on any polynomially connected weighted graph. Our algorithm draws a random spanning tree of the original graph and then predicts the nodes of this tree in constant expected amortized time and linear space. Experiments on real-world datasets show that our method compares well to both global (Perceptron) and local (label propagation) methods, while being generally faster in practice.


page 1

page 2

page 3

page 4


Active Learning on Trees and Graphs

We investigate the problem of active learning on a given tree whose node...

Spanning trees of smallest maximum degree in subdivisions of graphs

Given a graph G and a positive integer k, we study the question wheth...

Note on distributed certification of minimum spanning trees

A distributed proof (also known as local certification, or proof-labelin...

Recursive Prediction of Graph Signals with Incoming Nodes

Kernel and linear regression have been recently explored in the predicti...

Linear Algebra and Number of Spanning Trees

A network-theoretic approach for determining the complexity of a graph i...

An intelligent extension of Variable Neighbourhood Search for labelling graph problems

In this paper we describe an extension of the Variable Neighbourhood Sea...