Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks

Jing Gu, Dongmian Zou
Proceedings of the Second Learning on Graphs Conference, PMLR 231:14:1-14:29, 2024.

Abstract

Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder a comprehensive comparison. In this paper, we revisit datasets and approaches for unsupervised node-level graph anomaly detection tasks from three aspects. Firstly, we introduce outlier injection methods that create more diverse and graph-based anomalies in graph datasets. Secondly, we compare methods employing message passing against those without, uncovering the unexpected decline in performance associated with message passing. Thirdly, we explore the use of hyperbolic neural networks, specifying crucial architecture and loss design that contribute to enhanced performance. Through rigorous experiments and evaluations, our study sheds light on general strategies for improving node-level graph anomaly detection methods.

Cite this Paper


BibTeX
@InProceedings{pmlr-v231-gu24a, title = {Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks}, author = {Gu, Jing and Zou, Dongmian}, booktitle = {Proceedings of the Second Learning on Graphs Conference}, pages = {14:1--14:29}, year = {2024}, editor = {Villar, Soledad and Chamberlain, Benjamin}, volume = {231}, series = {Proceedings of Machine Learning Research}, month = {27--30 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v231/gu24a/gu24a.pdf}, url = {https://proceedings.mlr.press/v231/gu24a.html}, abstract = {Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder a comprehensive comparison. In this paper, we revisit datasets and approaches for unsupervised node-level graph anomaly detection tasks from three aspects. Firstly, we introduce outlier injection methods that create more diverse and graph-based anomalies in graph datasets. Secondly, we compare methods employing message passing against those without, uncovering the unexpected decline in performance associated with message passing. Thirdly, we explore the use of hyperbolic neural networks, specifying crucial architecture and loss design that contribute to enhanced performance. Through rigorous experiments and evaluations, our study sheds light on general strategies for improving node-level graph anomaly detection methods.} }
Endnote
%0 Conference Paper %T Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks %A Jing Gu %A Dongmian Zou %B Proceedings of the Second Learning on Graphs Conference %C Proceedings of Machine Learning Research %D 2024 %E Soledad Villar %E Benjamin Chamberlain %F pmlr-v231-gu24a %I PMLR %P 14:1--14:29 %U https://proceedings.mlr.press/v231/gu24a.html %V 231 %X Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder a comprehensive comparison. In this paper, we revisit datasets and approaches for unsupervised node-level graph anomaly detection tasks from three aspects. Firstly, we introduce outlier injection methods that create more diverse and graph-based anomalies in graph datasets. Secondly, we compare methods employing message passing against those without, uncovering the unexpected decline in performance associated with message passing. Thirdly, we explore the use of hyperbolic neural networks, specifying crucial architecture and loss design that contribute to enhanced performance. Through rigorous experiments and evaluations, our study sheds light on general strategies for improving node-level graph anomaly detection methods.
APA
Gu, J. & Zou, D.. (2024). Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks. Proceedings of the Second Learning on Graphs Conference, in Proceedings of Machine Learning Research 231:14:1-14:29 Available from https://proceedings.mlr.press/v231/gu24a.html.

Related Material