Measuring the Robustness of Graph Properties

12/03/2018
by   Yali Wan, et al.
0

In this paper, we propose a perturbation framework to measure the robustness of graph properties. Although there are already perturbation methods proposed to tackle this problem, they are limited by the fact that the strength of the perturbation cannot be well controlled. We firstly provide a perturbation framework on graphs by introducing weights on the nodes, of which the magnitude of perturbation can be easily controlled through the variance of the weights. Meanwhile, the topology of the graphs are also preserved to avoid uncontrollable strength in the perturbation. We then extend the measure of robustness in the robust statistics literature to the graph properties.

READ FULL TEXT
research
10/04/2022

Strength-Adaptive Adversarial Training

Adversarial training (AT) is proved to reliably improve network's robust...
research
06/07/2023

Perturbation of Fiedler vector: interest for graph measures and shape analysis

In this paper we investigate some properties of the Fiedler vector, the ...
research
03/10/2023

Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks

Graph neural networks (GNNs) have achieved state-of-the-art performance ...
research
07/16/2020

Learning perturbation sets for robust machine learning

Although much progress has been made towards robust deep learning, a sig...
research
03/24/2023

On the connection between the ABS perturbation methodology and differential privacy

This paper explores analytical connections between the perturbation meth...
research
01/29/2021

Topological Interference Management with Adversarial Perturbation

In this paper, we consider the topological interference management (TIM)...
research
08/16/2021

Robust Hierarchical Clustering for Directed Networks: An Axiomatic Approach

We provide a complete taxonomic characterization of robust hierarchical ...

Please sign up or login with your details

Forgot password? Click here to reset