Counting small cuts in a graph

TL;DR

This paper introduces a robust optimization method for counting small cuts in graphs under uncertainty, leveraging similarities across multiple graph measurements without assuming how they are obtained.

Contribution

It presents a novel robust optimization approach for the minimum cut problem that exploits similarities in graph data without specific assumptions.

Findings

Approach performs well compared to other oblivious methods.

Method effectively exploits similarities in multiple graph measurements.

Demonstrated robustness across various graph instances.

Abstract

We study the minimum cut problem in the presence of uncertainty and show how to apply a novel robust optimization approach, which aims to exploit the similarity in subsequent graph measurements or similar graph instances, without posing any assumptions on the way they have been obtained. With experiments we show that the approach works well when compared to other approaches that are also oblivious towards the relationship between the input datasets.