Multiple Network Embedding for Anomaly Detection in Time Series of Graphs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Guodong, Arroyo, Jesús, Athreya, Avanti, Cape, Joshua, Vogelstein, Joshua T., Park, Youngser, White, Chris, Larson, Jonathan, Yang, Weiwei, Priebe, Carey E.
Format: Preprint
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916324821696512
author Chen, Guodong
Arroyo, Jesús
Athreya, Avanti
Cape, Joshua
Vogelstein, Joshua T.
Park, Youngser
White, Chris
Larson, Jonathan
Yang, Weiwei
Priebe, Carey E.
author_facet Chen, Guodong
Arroyo, Jesús
Athreya, Avanti
Cape, Joshua
Vogelstein, Joshua T.
Park, Youngser
White, Chris
Larson, Jonathan
Yang, Weiwei
Priebe, Carey E.
contents This paper considers the graph signal processing problem of anomaly detection in time series of graphs. We examine two related, complementary inference tasks: the detection of anomalous graphs within a time series, and the detection of temporally anomalous vertices. We approach these tasks via the adaptation of statistically principled methods for joint graph inference, specifically \emph{multiple adjacency spectral embedding} (MASE). We demonstrate that our method is effective for our inference tasks. Moreover, we assess the performance of our method in terms of the underlying nature of detectable anomalies. We further provide the theoretical justification for our method and insight into its use. Applied to the Enron communication graph, a large-scale commercial search engine time series of graphs, and a larval Drosophila connectome data, our approaches demonstrate their applicability and identify the anomalous vertices beyond just large degree change.
format Preprint
id arxiv_https___arxiv_org_abs_2008_10055
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Multiple Network Embedding for Anomaly Detection in Time Series of Graphs
Chen, Guodong
Arroyo, Jesús
Athreya, Avanti
Cape, Joshua
Vogelstein, Joshua T.
Park, Youngser
White, Chris
Larson, Jonathan
Yang, Weiwei
Priebe, Carey E.
Methodology
This paper considers the graph signal processing problem of anomaly detection in time series of graphs. We examine two related, complementary inference tasks: the detection of anomalous graphs within a time series, and the detection of temporally anomalous vertices. We approach these tasks via the adaptation of statistically principled methods for joint graph inference, specifically \emph{multiple adjacency spectral embedding} (MASE). We demonstrate that our method is effective for our inference tasks. Moreover, we assess the performance of our method in terms of the underlying nature of detectable anomalies. We further provide the theoretical justification for our method and insight into its use. Applied to the Enron communication graph, a large-scale commercial search engine time series of graphs, and a larval Drosophila connectome data, our approaches demonstrate their applicability and identify the anomalous vertices beyond just large degree change.
title Multiple Network Embedding for Anomaly Detection in Time Series of Graphs
topic Methodology
url https://arxiv.org/abs/2008.10055