Lipschitz Continuous Algorithms for Graph Problems

11/09/2022
by   Soh Kumabe, et al.
0

It has been widely observed in the machine learning community that a small perturbation to the input can cause a large change in the prediction of a trained model, and such phenomena have been intensively studied in the machine learning community under the name of adversarial attacks. Because graph algorithms also are widely used for decision making and knowledge discovery, it is important to design graph algorithms that are robust against adversarial attacks. In this study, we consider the Lipschitz continuity of algorithms as a robustness measure and initiate a systematic study of the Lipschitz continuity of algorithms for (weighted) graph problems. Depending on how we embed the output solution to a metric space, we can think of several Lipschitzness notions. We mainly consider the one that is invariant under scaling of weights, and we provide Lipschitz continuous algorithms and lower bounds for the minimum spanning tree problem, the shortest path problem, and the maximum weight matching problem. In particular, our shortest path algorithm is obtained by first designing an algorithm for unweighted graphs that are robust against edge contractions and then applying it to the unweighted graph constructed from the original weighted graph. Then, we consider another Lipschitzness notion induced by a natural mapping that maps the output solution to its characteristic vector. It turns out that no Lipschitz continuous algorithm exists for this Lipschitz notion, and we instead design algorithms with bounded pointwise Lipschitz constants for the minimum spanning tree problem and the maximum weight bipartite matching problem. Our algorithm for the latter problem is based on an LP relaxation with entropy regularization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2023

Lower Bounds for Non-Adaptive Shortest Path Relaxation

We consider single-source shortest path algorithms that perform a sequen...
research
07/17/2023

Lipschitz Continuous Algorithms for Covering Problems

Combinatorial algorithms are widely used for decision-making and knowled...
research
05/17/2020

Robust Algorithms for TSP and Steiner Tree

Robust optimization is a widely studied area in operations research, whe...
research
07/04/2012

Theory and Techniques for Synthesizing a Family of Graph Algorithms

Although Breadth-First Search (BFS) has several advantages over Depth-Fi...
research
06/23/2018

Approximating some network problems with scenarios

In this paper the shortest path and the minimum spanning tree problems i...
research
08/22/2020

Improved Weighted Additive Spanners

Graph spanners and emulators are sparse structures that approximately pr...
research
11/29/2013

Statistical estimation for optimization problems on graphs

Large graphs abound in machine learning, data mining, and several relate...

Please sign up or login with your details

Forgot password? Click here to reset