Graph Neural Network-Based Anomaly Detection in Multivariate Time Series

Deng, Ailin; Hooi, Bryan

doi:10.1609/aaai.v35i5.16523

Cited by 378 publications

(129 citation statements)

References 36 publications

Supporting

Mentioning

129

Contrasting

Order By: Relevance

“…In addition, GNNs have been used to perform anomaly detection in time series data. [11] propose an attention-based GNN that used the results of a forecast to classify deviating predictions as anomalies. In addition, [12] propose GRIL (graph recurrent imputation layer), a spatial-temporal GNN that reconstructs missing data by learning spatial-temporal representations.…”

Section: Graph Neural Network For Time Series Analysismentioning

confidence: 99%

“…Consequently, researchers have developed deep learning techniques to perform time series analysis like forecasting [10], anomaly detection [11] and imputation [12], with data arising from networks (i. e., graphs), called graph neural networks (now referred to as GNNs), which we also focus on in this paper. However, if the predicted value does not rely more on recent values from the input than early values (known as Time Series Extrinsic Regression (TSER) [7]), the aforementioned models are not adequate for the task.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph neural networks for multivariate time series regression with application to seismic data

Bloemheuvel

Hoogen

Jozinović

et al. 2022

Int J Data Sci Anal

View full text Add to dashboard Cite

Machine learning, with its advances in deep learning has shown great potential in analyzing time series. In many scenarios, however, additional information that can potentially improve the predictions is available. This is crucial for data that arise from e. g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time series) information. Recent advances in adapting deep learning to graphs have shown potential in various tasks. However, these methods have not been adapted for time series tasks to a great extent. Most attempts have essentially consolidated around time series forecasting with small sequence lengths. Generally, these architectures are not well suited for regression or classification tasks where the value to be predicted is not strictly depending on the most recent values, but rather on the whole length of the time series. We propose TISER-GCN, a novel graph neural network architecture for processing, in particular, these long time series in a multivariate regression task. Our proposed model is tested on two seismic datasets containing earthquake waveforms, where the goal is to predict maximum intensity measurements of ground shaking at each seismic station. Our findings demonstrate promising results of our approach—with an average MSE reduction of 16.3%—compared to the best performing baselines. In addition, our approach matches the baseline scores by needing only half the input size. The results are discussed in depth with an additional ablation study.

show abstract

Section: Graph Neural Network For Time Series Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Graph neural networks for multivariate time series regression with application to seismic data

Bloemheuvel

Hoogen

Jozinović

et al. 2022

Int J Data Sci Anal

View full text Add to dashboard Cite

show abstract

“…This is especially crucial in power grids, water treatment facilities, and communication networks because as complexity develops, it becomes more difficult to spot anomalies. In [ 15 ], they introduced a novel graph deviation network to learn the sensor relationship graph. Four components comprise the approach: sensor embedding, graph structure learning, attention-based forecasting, and deviation score.…”

Section: Related Workmentioning

confidence: 99%

MTEDS: Multivariant Time Series-Based Encoder-Decoder System for Anomaly Detection

Reyana

Kautish²,

Yahia

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Intrusion detection systems examine the computer or network for potential security vulnerabilities. Time series data is real-valued. The nature of the data influences the type of anomaly detection. As a result, network anomalies are operations that deviate from the norm. These anomalies can cause a wide range of device malfunctions, overloads, and network intrusions. As a result of this, the network’s normal operation and services will be disrupted. The paper proposes a new multi-variant time series-based encoder-decoder system for dealing with anomalies in time series data with multiple variables. As a result, to update network weights via backpropagation, a radical loss function is defined. Anomaly scores are used to evaluate performance. The anomaly score, according to the findings, is more stable and traceable, with fewer false positives and negatives. The proposed system’s efficiency is compared to three existing approaches: Multiscaling Convolutional Recurrent Encoder-Decoder, Autoregressive Moving Average, and Long Short Term Medium-Encoder-Decoder. The results show that the proposed technique has the highest precision of 1 for a noise level of 0.2. Thus, it demonstrates greater precision for noise factors of 0.25, 0.3, 0.35, and 0.4, and its effectiveness.

show abstract

“…Since GNN-based methods are inherently less interpretable than traditional machine learning approaches, it is important to resolve the issue along with explainable models for anomaly detection. Currently, there is relatively little work on designing explainable GNN models for graph anomaly detection (e.g., Deng et al [58]).…”

Section: A: Explainable Gnns For Detecting Graph Anomaliesmentioning

confidence: 99%

Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges

et al. 2022

View full text Add to dashboard Cite

Graphs are used widely to model complex systems, and detecting anomalies in a graph is an important task in the analysis of complex systems. Graph anomalies are patterns in a graph that do not conform to normal patterns expected of the attributes and/or structures of the graph. In recent years, graph neural networks (GNNs) have been studied extensively and have successfully performed difficult machine learning tasks in node classification, link prediction, and graph classification thanks to the highly expressive capability via message passing in effectively learning graph representations. To solve the graph anomaly detection problem, GNN-based methods leverage information about the graph attributes (or features) and/or structures to learn to score anomalies appropriately. In this survey, we review the recent advances made in detecting graph anomalies using GNN models. Specifically, we summarize GNN-based methods according to the graph type (i.e., static and dynamic), the anomaly type (i.e., node, edge, subgraph, and whole graph), and the network architecture (e.g., graph autoencoder, graph convolutional network). To the best of our knowledge, this survey is the first comprehensive review of graph anomaly detection methods based on GNNs.

show abstract

Graph Neural Network-Based Anomaly Detection in Multivariate Time Series

Cited by 378 publications

References 36 publications

Graph neural networks for multivariate time series regression with application to seismic data

Graph neural networks for multivariate time series regression with application to seismic data

MTEDS: Multivariant Time Series-Based Encoder-Decoder System for Anomaly Detection

Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges

Contact Info

Product

Resources

About