Deep anomaly detection on attributed networks

Kaize Ding, Jundong Li, Rohit Bhanushali, Huan Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Attributed networks are ubiquitous and form a critical component of modern information infrastructure, where additional node attributes complement the raw network structure in knowledge discovery. Recently, detecting anomalous nodes on attributed networks has attracted an increasing amount of research attention, with broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Most of the existing attempts, however, tackle the problem with shallow learning mechanisms by ego-network or community analysis, or through subspace selection. Undoubtedly, these models cannot fully address the computational challenges on attributed networks. For example, they often suffer from the network sparsity and data nonlinearity issues, and fail to capture the complex interactions between different information modalities, thus negatively impact the performance of anomaly detection. To tackle the aforementioned problems, in this paper, we study the anomaly detection problem on attributed networks by developing a novel deep model. In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data. The synergy between GCN and autoencoder enables us to spot anomalies by measuring the reconstruction errors of nodes from both the structure and the attribute perspectives. Extensive experiments on real-world attributed network datasets demonstrate the efficacy of our proposed algorithm.

Original languageEnglish (US)
Title of host publicationSIAM International Conference on Data Mining, SDM 2019
PublisherSociety for Industrial and Applied Mathematics Publications
Pages594-602
Number of pages9
ISBN (Electronic)9781611975673
StatePublished - Jan 1 2019
Event19th SIAM International Conference on Data Mining, SDM 2019 - Calgary, Canada
Duration: May 2 2019May 4 2019

Publication series

NameSIAM International Conference on Data Mining, SDM 2019

Conference

Conference19th SIAM International Conference on Data Mining, SDM 2019
CountryCanada
CityCalgary
Period5/2/195/4/19

Fingerprint

Finance
Data mining
Experiments

Keywords

  • Anomaly Detection
  • Attributed Networks
  • Deep Autoencoder
  • Graph Convolutional Network

ASJC Scopus subject areas

  • Software

Cite this

Ding, K., Li, J., Bhanushali, R., & Liu, H. (2019). Deep anomaly detection on attributed networks. In SIAM International Conference on Data Mining, SDM 2019 (pp. 594-602). (SIAM International Conference on Data Mining, SDM 2019). Society for Industrial and Applied Mathematics Publications.

Deep anomaly detection on attributed networks. / Ding, Kaize; Li, Jundong; Bhanushali, Rohit; Liu, Huan.

SIAM International Conference on Data Mining, SDM 2019. Society for Industrial and Applied Mathematics Publications, 2019. p. 594-602 (SIAM International Conference on Data Mining, SDM 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ding, K, Li, J, Bhanushali, R & Liu, H 2019, Deep anomaly detection on attributed networks. in SIAM International Conference on Data Mining, SDM 2019. SIAM International Conference on Data Mining, SDM 2019, Society for Industrial and Applied Mathematics Publications, pp. 594-602, 19th SIAM International Conference on Data Mining, SDM 2019, Calgary, Canada, 5/2/19.
Ding K, Li J, Bhanushali R, Liu H. Deep anomaly detection on attributed networks. In SIAM International Conference on Data Mining, SDM 2019. Society for Industrial and Applied Mathematics Publications. 2019. p. 594-602. (SIAM International Conference on Data Mining, SDM 2019).
Ding, Kaize ; Li, Jundong ; Bhanushali, Rohit ; Liu, Huan. / Deep anomaly detection on attributed networks. SIAM International Conference on Data Mining, SDM 2019. Society for Industrial and Applied Mathematics Publications, 2019. pp. 594-602 (SIAM International Conference on Data Mining, SDM 2019).
@inproceedings{45c34e6922e34aa58a8ae4c1f52dc78a,
title = "Deep anomaly detection on attributed networks",
abstract = "Attributed networks are ubiquitous and form a critical component of modern information infrastructure, where additional node attributes complement the raw network structure in knowledge discovery. Recently, detecting anomalous nodes on attributed networks has attracted an increasing amount of research attention, with broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Most of the existing attempts, however, tackle the problem with shallow learning mechanisms by ego-network or community analysis, or through subspace selection. Undoubtedly, these models cannot fully address the computational challenges on attributed networks. For example, they often suffer from the network sparsity and data nonlinearity issues, and fail to capture the complex interactions between different information modalities, thus negatively impact the performance of anomaly detection. To tackle the aforementioned problems, in this paper, we study the anomaly detection problem on attributed networks by developing a novel deep model. In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data. The synergy between GCN and autoencoder enables us to spot anomalies by measuring the reconstruction errors of nodes from both the structure and the attribute perspectives. Extensive experiments on real-world attributed network datasets demonstrate the efficacy of our proposed algorithm.",
keywords = "Anomaly Detection, Attributed Networks, Deep Autoencoder, Graph Convolutional Network",
author = "Kaize Ding and Jundong Li and Rohit Bhanushali and Huan Liu",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
series = "SIAM International Conference on Data Mining, SDM 2019",
publisher = "Society for Industrial and Applied Mathematics Publications",
pages = "594--602",
booktitle = "SIAM International Conference on Data Mining, SDM 2019",

}

TY - GEN

T1 - Deep anomaly detection on attributed networks

AU - Ding, Kaize

AU - Li, Jundong

AU - Bhanushali, Rohit

AU - Liu, Huan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Attributed networks are ubiquitous and form a critical component of modern information infrastructure, where additional node attributes complement the raw network structure in knowledge discovery. Recently, detecting anomalous nodes on attributed networks has attracted an increasing amount of research attention, with broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Most of the existing attempts, however, tackle the problem with shallow learning mechanisms by ego-network or community analysis, or through subspace selection. Undoubtedly, these models cannot fully address the computational challenges on attributed networks. For example, they often suffer from the network sparsity and data nonlinearity issues, and fail to capture the complex interactions between different information modalities, thus negatively impact the performance of anomaly detection. To tackle the aforementioned problems, in this paper, we study the anomaly detection problem on attributed networks by developing a novel deep model. In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data. The synergy between GCN and autoencoder enables us to spot anomalies by measuring the reconstruction errors of nodes from both the structure and the attribute perspectives. Extensive experiments on real-world attributed network datasets demonstrate the efficacy of our proposed algorithm.

AB - Attributed networks are ubiquitous and form a critical component of modern information infrastructure, where additional node attributes complement the raw network structure in knowledge discovery. Recently, detecting anomalous nodes on attributed networks has attracted an increasing amount of research attention, with broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Most of the existing attempts, however, tackle the problem with shallow learning mechanisms by ego-network or community analysis, or through subspace selection. Undoubtedly, these models cannot fully address the computational challenges on attributed networks. For example, they often suffer from the network sparsity and data nonlinearity issues, and fail to capture the complex interactions between different information modalities, thus negatively impact the performance of anomaly detection. To tackle the aforementioned problems, in this paper, we study the anomaly detection problem on attributed networks by developing a novel deep model. In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data. The synergy between GCN and autoencoder enables us to spot anomalies by measuring the reconstruction errors of nodes from both the structure and the attribute perspectives. Extensive experiments on real-world attributed network datasets demonstrate the efficacy of our proposed algorithm.

KW - Anomaly Detection

KW - Attributed Networks

KW - Deep Autoencoder

KW - Graph Convolutional Network

UR - http://www.scopus.com/inward/record.url?scp=85066080876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066080876&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85066080876

T3 - SIAM International Conference on Data Mining, SDM 2019

SP - 594

EP - 602

BT - SIAM International Conference on Data Mining, SDM 2019

PB - Society for Industrial and Applied Mathematics Publications

ER -