Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence 2017
DOI: 10.24963/ijcai.2017/433
|View full text |Cite
|
Sign up to set email alerts
|

Query-Driven Discovery of Anomalous Subgraphs in Attributed Graphs

Abstract: For a detection problem, a user often has some prior knowledge about the structure-specific subgraphs of interest, but few traditional approaches are capable of employing this knowledge. The main technical challenge is that few approaches can efficiently model the space of connected subgraphs that are isomorphic to a query graph. We present a novel, efficient approach for optimizing a generic nonlinear cost function subject to a query-specific structural constraint. Our approach enjoys strong theoretical guara… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
9
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(9 citation statements)
references
References 14 publications
0
9
0
Order By: Relevance
“…In numerous network applications, the computer network data of interest consist of "star-shape" attacking subgraphs (Wu et al 2017), and the political blog data of interest consist of "core-periphery" graph shape anomalies (Zhang, Martin, and Newman 2015). Anomalies appear in the real network applications in the form of specific-shapes rather than point shapes.…”
Section: Introductionmentioning
confidence: 99%
See 4 more Smart Citations
“…In numerous network applications, the computer network data of interest consist of "star-shape" attacking subgraphs (Wu et al 2017), and the political blog data of interest consist of "core-periphery" graph shape anomalies (Zhang, Martin, and Newman 2015). Anomalies appear in the real network applications in the form of specific-shapes rather than point shapes.…”
Section: Introductionmentioning
confidence: 99%
“…Graph-structured matching pursuit (Chen and Zhou 2016) and Graph-CoSaMP (Hegde, Indyk, and Schmidt 2015) approaches are proposed to connected subgraph anomaly detection by general nonlinear functions. The graph tree projection pursuit approach (Wu et al 2017) can employ the nonlinear cost functions, such as Kulldorff (Kulldorff 1997) and Expectation-based Poisson (EBP) graph scan statistics (Neill 2009b), to the tree shape graph anomaly detection. The specific-shape prior can be used to the powerful nonlinear cost function for anomaly detection in attributed graphs with network structures and vertex attributes.…”
Section: Introductionmentioning
confidence: 99%
See 3 more Smart Citations