2022

Rethinking Graph Neural Networks for Anomaly Detection

Tang, Jianheng, Li, Jiajin, Gao, Ziqi et al.

Understand

Graph Neural Networks (GNNs) are widely applied for graph anomaly detection.

As one of the key components for GNN design is to select a tailored spectral filter, we take the first step towards analyzing anomalies via the lens of the graph spectrum.
Our crucial observation is the existence of anomalies will lead to the `right-shift' phenomenon, that is, the spectral energy distribution concentrates less on low frequencies and more on high frequencies.
This fact motivates us to propose the Beta Wavelet Graph Neural Network (BWGNN).

Built on

Deep graph library: A graph-centric, highly-performant package for graph neural networks
Original
Wang, M., Zheng, D., Ye, Z., Gan, Q., Li, M., Song, X., Zhou, J., Ma, C., Yu, L., Gai, Y., Xiao, T., He, T., Karypis, G., Li, J., and Zhang, Z · 1909
Earlier work this paper cites.
The advanced theory of statistics
Kendall, M. G. et al · 1946
Earlier work this paper cites.
Procedures for detecting outlying observations in samples
Grubbs, F. E · 1969
Earlier work this paper cites.
On the use of the coefficient of variation as a measure of diversity
Bedeian, A. G. and Mossholder, K. W · 2000
Earlier work this paper cites.
Graph-based anomaly detection
Noble, C. C. and Cook, D. J · 2003
Earlier work this paper cites.
Beta wavelets. synthesis and application to lossy image compression
Amar, C. B., Zaied, M., and Alimi, A · 2005
Earlier work this paper cites.
Diffusion wavelets
Coifman, R. R. and Maggioni, M · 2006
Earlier work this paper cites.
The relationship between precision-recall and roc curves
Davis, J. and Goadrich, M · 2006
Earlier work this paper cites.
Spectral graph theory and its applications
Spielman, D. A · 2007
Earlier work this paper cites.
Fbwn: An architecture of fast beta wavelet networks for image classification
Jemai, O., Zaied, M., Amar, C. B., and Alimi, A. M · 2010
Earlier work this paper cites.
Libsvm: a library for support vector machines
Chang, C.-C. and Lin, C.-J · 2011
Earlier work this paper cites.
Wavelets on graphs via spectral graph theory
Hammond, D. K., Vandergheynst, P., and Gribonval, R · 2011
Earlier work this paper cites.
Data Mining: Concepts and Techniques, 3rd edition
Han, J., Kamber, M., and Pei, J · 2011
Earlier work this paper cites.
The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature
Ngai, E. W., Hu, Y., Wong, Y. H., Chen, Y., and Sun, X · 2011
Earlier work this paper cites.
Scikit-learn: Machine learning in python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al · 2011
Earlier work this paper cites.
Anomaly detection for cybersecurity of the substations
Ten, C.-W., Hong, J., and Liu, C.-C · 2011
Earlier work this paper cites.
From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews
McAuley, J. J. and Leskovec, J · 2013
Earlier work this paper cites.
Gspbox: A toolbox for signal processing on graphs
Original
Perraudin, N., Paratte, J., Shuman, D., Martin, L., Kalofolias, V., Vandergheynst, P., and Hammond, D. K · 2014
Earlier work this paper cites.

Similar

Compactly supported one-cyclic wavelets derived from beta distributions
Original
De Oliveira, H. and De Araújo, G · 2015
Cited alongside, same era.
Collective opinion spam detection: Bridging review networks and metadata
Rayana, S. and Akoglu, L · 2015
Cited alongside, same era.
Convolutional neural networks on graphs with fast localized spectral filtering
Defferrard, M., Bresson, X., and Vandergheynst, P · 2016
Cited alongside, same era.
Fast beta wavelet network-based feature extraction for image copy detection
ElAdel, A., Zaied, M., and Amar, C. B · 2016
Cited alongside, same era.
Inductive representation learning on large graphs
Hamilton, W. L., Ying, R., and Leskovec, J · 2017
Cited alongside, same era.
Semi-supervised classification with graph convolutional networks
Kipf, T. N. and Welling, M · 2017
Cited alongside, same era.
Graph attention networks
Original
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y · 2017
Cited alongside, same era.
Learning structural node embeddings via diffusion wavelets
Donnat, C., Zitnik, M., Hallac, D., and Leskovec, J · 2018
Cited alongside, same era.
Rev2: Fraudulent user prediction in rating platforms
Kumar, S., Hooi, B., Makhija, D., Kumar, M., Faloutsos, C., and Subrahmanian, V · 2018
Cited alongside, same era.
Cayleynets: Graph convolutional neural networks with complex rational spectral filters
Levie, R., Monti, F., Bresson, X., and Bronstein, M. M · 2018
Cited alongside, same era.
Deeper insights into graph convolutional networks for semi-supervised learning
Li, Q., Han, Z., and Wu, X · 2018
Cited alongside, same era.
Outlier aware network embedding for attributed networks
Bandyopadhyay, S., Lokesh, N., and Murty, M. N · 2019
Cited alongside, same era.

Then

Simplifying graph convolutional networks
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K · 2019
Later among the works it cites.
Analyzing the expressive power of graph neural networks in a spectral perspective
Balcilar, M., Renton, G., Héroux, P., Gaüzère, B., Adam, S., and Honeine, P · 2020
Later among the works it cites.
Deterrent: Knowledge guided graph attention network for detecting healthcare misinformation
Cui, L., Seo, H., Tabar, M., Ma, F., Wang, S., and Lee, D · 2020
Later among the works it cites.
Enhancing graph neural network-based fraud detectors against camouflaged fraudsters
Dou, Y., Liu, Z., Sun, L., Deng, Y., Peng, H., and Yu, P. S · 2020
Later among the works it cites.
Alleviating the inconsistency problem of applying graph neural network to fraud detection
Liu, Z., Dou, Y., Yu, P. S., Deng, Y., and Peng, H · 2020
Later among the works it cites.
Scattering GCN: overcoming oversmoothness in graph convolutional networks
Min, Y., Wenkel, F., and Wolf, G · 2020
Later among the works it cites.
Interpretable, multidimensional, multimodal anomaly detection with negative sampling for detection of device failure
Sipple, J · 2020
Later among the works it cites.
Error-bounded graph anomaly loss for gnns
Zhao, T., Deng, C., Yu, K., Jiang, T., Wang, D., and Jiang, M · 2020
Later among the works it cites.
Beyond low-frequency information in graph convolutional networks
Bo, D., Wang, X., Shi, C., and Shen, H · 2021
Later among the works it cites.
Adagnn: Graph neural networks with adaptive frequency response filter
Dong, Y., Ding, K., Jalaian, B., Ji, S., and Li, J · 2021
Later among the works it cites.
Bernnet: Learning arbitrary graph spectral filters via bernstein approximation
He, M., Wei, Z., Huang, Z., and Xu, H · 2021
Later among the works it cites.
Deconvolutional networks on graph data
Li, J., Li, J., Liu, Y., Yu, J., Li, Y., and Cheng, H · 2021
Later among the works it cites.
Pick and choose: A gnn-based imbalanced learning approach for fraud detection
Liu, Y., Ao, X., Qin, Z., Chi, J., Feng, J., Yang, H., and He, Q · 2021
Later among the works it cites.
A comprehensive survey on graph anomaly detection with deep learning
Ma, X., Wu, J., Xue, S., Yang, J., Zhou, C., Sheng, Q. Z., Xiong, H., and Akoglu, L · 2021
Later among the works it cites.
Geometric scattering attention networks
Min, Y., Wenkel, F., and Wolf, G · 2021
Later among the works it cites.
Beyond low-pass filtering: Graph convolutional networks with automatic filtering
Original
Wu, Z., Pan, S., Long, G., Jiang, J., and Zhang, C · 2021
Later among the works it cites.
A synergistic approach for graph anomaly detection with pattern mining and feature learning
Zhao, T., Jiang, T., Shah, N., and Jiang, M · 2021
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…