[en] This work proposes a graph model for networks where node collaborations can be described by the Markov property. The proposed model augments an initial graph adjacency using diffusion distances. The resulting virtual adjacency depends on a diffusion-scale parameter, which leads to a controlled shift in the graph-Fourier-transform spectrum. This enables a frequency analysis tailored to the actual network collaboration, revealing more information on the graph signal when compared to traditional approaches. The proposed model is employed for anomaly detection in real and synthetic networks, and results confirm that using the proposed virtual adjacency yields better classification than the initial adjacency.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Elias, Vitor R. M.
Alves Martins, Wallace ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Werner, Stefan
External co-authors :
yes
Language :
English
Title :
Diffusion-based Virtual Graph Adjacency for Fourier Analysis of Network Signals
Publication date :
November 2020
Event name :
XXXVIII SIMPÓSIO BRASILEIRO DE TELECOMUNICAÇÕES E PROCESSAMENTO DE SINAIS
Event place :
Brazil
Event date :
from 22-11-2020 to 25-11-2020
Main work title :
XXXVIII SIMPÓSIO BRASILEIRO DE TELECOMUNICAÇÕES E PROCESSAMENTO DE SINAIS, Florianópolis 22-25 November 2020
Peer reviewed :
Peer reviewed
European Projects :
H2020 - 742648 - AGNOSTIC - Actively Enhanced Cognition based Framework for Design of Complex Systems