Graph Neural Network Solutions for Anomaly Detection in Time Series

Simple item page
dc.contributor.authorCornali, Roberto
dc.contributor.authorRonchieri, Elisabetta
dc.contributor.authorCesini, Daniele
dc.contributor.authorDell’Agnello, Luca
dc.date.accessioned2024-12-26T21:05:12Z
dc.date.available2024-12-26T21:05:12Z
dc.date.issued2025-01-07
dc.description.abstractAnomaly detection is an essential task for many firms and organizations. Identifying unusual patterns in messy multivariate time series can prevent catastrophic events and optimize operations. Traditional statistical methods struggle with high-dimensional data and complex temporal dependencies. In this paper, we propose a novel approach, combining Generative Adversarial Networks (GANs), a reconstruction-based framework, and Graph Neural Networks (GNNs) for effective and interpretable anomaly detection. Our method involves representing multivariate times series as graphs and training two interconnected GANs and an Autoencoder to capture the normal behavior of the networks. Anomalies are detected by measuring the reconstruction error and the discriminator's score. Our case study on the signals of the INFN CNAF Tier-1 data center demonstrates the effectiveness of our approach in terms of robustness and interpretability. We validate our model on NASA's public space telemetry signals, a popular multivariate time series benchmark and observe cutting-edge performance. This work highlights the potential of GNNs in developing interpretable deep learning solutions for real-world applications.
dc.format.extent10
dc.identifier.doi10.24251/HICSS.2025.119
dc.identifier.isbn978-0-9981331-8-8
dc.identifier.other2c5aeb18-84dd-4b86-9c32-22d8170955c9
dc.identifier.urihttps://hdl.handle.net/10125/108957
dc.relation.ispartofProceedings of the 58th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectArtificial Intelligence-powered Devices and Sensors
dc.subjectanomaly detection, generative adversarial network, graph neural network, interpretable deep learning, time series
dc.titleGraph Neural Network Solutions for Anomaly Detection in Time Series
dc.typeConference Paper
dc.type.dcmiText
prism.startingpage997

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0099.pdf
Size:
1.27 MB
Format:
Adobe Portable Document Format
Download

Collections

Artificial Intelligence-powered Devices and Sensors