Rethinking Graph Neural Networks for Anomaly Detection

Jianheng Tang, Jiajin Li, Ziqi Gao, Jia Li
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:21076-21089, 2022.

Abstract

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). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the ‘right-shift’ phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-tang22b, title = {Rethinking Graph Neural Networks for Anomaly Detection}, author = {Tang, Jianheng and Li, Jiajin and Gao, Ziqi and Li, Jia}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {21076--21089}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/tang22b/tang22b.pdf}, url = {https://proceedings.mlr.press/v162/tang22b.html}, abstract = {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). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the ‘right-shift’ phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection.} }
Endnote
%0 Conference Paper %T Rethinking Graph Neural Networks for Anomaly Detection %A Jianheng Tang %A Jiajin Li %A Ziqi Gao %A Jia Li %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-tang22b %I PMLR %P 21076--21089 %U https://proceedings.mlr.press/v162/tang22b.html %V 162 %X 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). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the ‘right-shift’ phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection.
APA
Tang, J., Li, J., Gao, Z. & Li, J.. (2022). Rethinking Graph Neural Networks for Anomaly Detection. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:21076-21089 Available from https://proceedings.mlr.press/v162/tang22b.html.

Related Material