Abstract
Accurate and timely detection of large events on urban transportation networks enables informed mobility management. This work tackles the problem of extreme event detection on large-scale transportation networks using origin-destination mobility data, which is now widely available. Such data is highly structured in time and space, but high dimensional and sparse. Current multivariate time series anomaly detection methods cannot fully address these challenges. To exploit the structure of mobility data, we formulate the event detection problem in a novel way, as detecting anomalies in a set of time-dependent directed weighted graphs. We further propose a Context augmented Graph Autoencoder (Con-GAE) model to solve the problem, which leverages graph embedding and context embedding techniques to capture the spatial and temporal patterns. Con-GAE adopts an autoencoder framework and detects anomalies via semi-supervised learning. The performance of the method is assessed on several city-scale travel-time datasets from Uber Movement, New York taxis, and Chicago taxis and compared to state-of-the-art approaches. The proposed Con-GAE can achieve an improvement in the area under the curve score as large as 0.15 over the second best method. We also discuss real-world traffic anomalies detected by Con-GAE.
- [1] . 2015. Graph based anomaly detection and description: A survey. Data Min. Knowl. Discov. 29, 3 (2015), 626–688.Google ScholarDigital Library
- [2] . 2020. USAD: UnSupervised anomaly detection on multivariate time series. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 3395–3404.Google ScholarDigital Library
- [3] . 2018. Graph convolutional matrix completion. In Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD’18).Google Scholar
- [4] . 2022. Graph Neural Networks With Convolutional Arma Filters. In IEEE Trans. Pattern Anal. Mach. Intell. 44, 7 (2022), 3496–3507.
DOI: 10.1109/TPAMI.2021.3054830Google Scholar - [5] . 2019. Anomaly detection using autoencoders in high performance computing systems. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 9428–9433.Google ScholarDigital Library
- [6] . 2005. Algorithms for rapid outbreak detection: A research synthesis. J. Biomed. Inform. 38, 2 (2005), 99–113.Google ScholarDigital Library
- [7] . 2020. Anomalous example detection in deep learning: A survey. IEEE Access 8 (2020), 132330–132347.Google ScholarCross Ref
- [8] . 2021. Dynamic planning of bicycle stations in dockless public bicycle-sharing system using gated graph neural network. ACM Trans. Intell. Syst. Technol. 12, 2 (2021), 1–22.Google ScholarDigital Library
- [9] . 2020. Divvy Trips. Retrieved Nov. 2020 from https://data.cityofchicago.org/Transportation/Divvy-Trips/fg6s-gzvg.Google Scholar
- [10] . 2020. Taxi Trips. Retrieved Nov. 2020 from https://data.cityofchicago.org/Transportation/Taxi-Trips/wrvz-psew.Google Scholar
- [11] . 2017. Abnormal event detection in videos using spatiotemporal autoencoder. In Proceedings of the International Symposium on Neural Networks. Springer, 189–196.Google ScholarCross Ref
- [12] . 2019. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 890–897.Google ScholarDigital Library
- [13] . 2019. Deep anomaly detection on attributed networks. In Proceedings of the SIAM International Conference on Data Mining. SIAM, 594–602.Google ScholarCross Ref
- [14] . 2017. Topology adaptive graph convolutional networks. Retrieved from https://arXiv:1710.10370.Google Scholar
- [15] . 2020. Benchmarking graph neural networks. Retrieved from https://arXiv:2003.00982.Google Scholar
- [16] . 2020. AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’20). IEEE, 5685–5689.Google ScholarCross Ref
- [17] . 2016. Event detection from traffic tensors: A hybrid model. Neurocomputing 203 (2016), 22–33.Google ScholarDigital Library
- [18] . 2019. Fast graph representation learning with PyTorch geometric. In Proceedings of the ICLR Workshop on Representation Learning on Graphs and Manifolds.Google Scholar
- [19] . 2019. Anomaly Detection on Time Series: An Evaluation of Deep Learning Methods. Retrieved from https://github.com/KDD-OpenSource/DeepADoTS.Google Scholar
- [20] . 2014. Robust low-rank tensor recovery: Models and algorithms. SIAM J. Matrix Anal. Appl. 35, 1 (2014), 225–253.Google ScholarDigital Library
- [21] . 2018. Dyngem: Deep embedding method for dynamic graphs. Retrieved from https://arXiv:1805.11273.Google Scholar
- [22] . 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. MIT Press, 1024–1034.Google Scholar
- [23] . 2002. Outlier detection using replicator neural networks. In Proceedings of the International Conference on Data Warehousing and Knowledge Discovery. Springer, 170–180.Google ScholarDigital Library
- [24] . 2020. Robust tensor recovery with fiber outliers for traffic events. ACM Trans. Knowl. Discov. Data 15, 1 (2020), 1–27.Google ScholarDigital Library
- [25] . 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR’15).Google Scholar
- [26] . 2016. Variational graph auto-encoders. Retrieved from https://arXiv:1611.07308.Google Scholar
- [27] . 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR’17).Google Scholar
- [28] . 2020. Deep detection of anomalies in static attributed graph. In Proceedings of the International Conference on Machine Learning, Image Processing, Network Security and Data Sciences. Springer, 627–640.Google ScholarCross Ref
- [29] . 2020. Semi-supervised anomaly detection on attributed graphs. Retrieved from https://arXiv:2002.12011.Google Scholar
- [30] . 2021. Spatiotemporal attention-based graph convolution network for segment-level traffic prediction. IEEE Trans. Intell. Transport. Syst. (2021), 1–9. Google ScholarDigital Library
- [31] . 2019. SpecAE: Spectral AutoEncoder for anomaly detection in attributed networks. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2233–2236.Google ScholarDigital Library
- [32] . 2019. A hybrid deep learning approach with GCN and LSTM for traffic flow prediction. In Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC’19). 1929–1933. Google ScholarDigital Library
- [33] . 2016. LSTM-based encoder-decoder for multi-sensor anomaly detection. Retrieved from https://arXiv:1607.00148.Google Scholar
- [34] . 2014. A Guide to Regional Transportation Planning for Disasters, Emergencies, and Significant Events. National Cooperative Highway Research Program (NCHRP) Report 777, Project No. NCHRP 20-59(42). TRB Publications.Google ScholarCross Ref
- [35] . 2020. Social-STGCNN: A social spatio-temporal graph convolutional neural network for human trajectory prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14424–14432.Google ScholarCross Ref
- [36] . 2019. 2019 NFL Draft Event Schedule. Retrieved from https://www.visitmusiccity.com/nfldraft/nfl-draft-event-schedule.Google Scholar
- [37] . 2021. Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Info. Sci. 578 (2021), 401–416. Google ScholarDigital Library
- [38] . 2014. Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2nd Workshop on Machine Learning for Sensory Data Analysis. 4–11.Google ScholarDigital Library
- [39] . 2018. Modeling relational data with graph convolutional networks. In Proceedings of the European Semantic Web Conference. Springer, 593–607.Google ScholarDigital Library
- [40] . 2020. Masked label prediction: Unified message passing model for semi-supervised classification. Retrieved from https://arXiv:2009.03509.Google Scholar
- [41] . 2014. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1 (2014), 1929–1958.Google ScholarDigital Library
- [42] . 2019. Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2828–2837.Google ScholarDigital Library
- [43] . 2013. Traffic volume data outlier recovery via tensor model. Math. Problems Eng. 2013 (2013).Google ScholarCross Ref
- [44] . 2019. TDOT Weekly Construction Report for Middle Tennessee. Retrieved from https://preprod.tn.gov/tdot/news/2019/4/17/tdot-weekly-construction-report-for-middle-tennessee--april-18-24--2019.html.Google Scholar
- [45] . 2014. Learning deep representations for graph clustering. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI’14), Vol. 14. 1293–1299.Google ScholarCross Ref
- [46] . 2020. TLC Trip Record Data. Retrieved from https://www1.nyc.gov/site/tlc/index.page.Google Scholar
- [47] . 2020. Uber Movement. Retrieved from https://movement.uber.com/.Google Scholar
- [48] . 2017. Graph attention networks. Retrieved from https://arXiv:1710.10903.Google Scholar
- [49] . 2017. Mgae: Marginalized graph autoencoder for graph clustering. In Proceedings of the ACM on Conference on Information and Knowledge Management. 889–898.Google ScholarDigital Library
- [50] . 2020. On representation learning for road networks. ACM Trans. Intell. Syst. Technol. 12, 1 (2020), 1–27.Google Scholar
- [51] . 2019. Origin-destination matrix prediction via graph convolution: A new perspective of passenger demand modeling. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1227–1235.Google ScholarDigital Library
- [52] . 2021. Gallat: A spatiotemporal graph attention network for passenger demand prediction. In Proceedings of the IEEE 37th International Conference on Data Engineering (ICDE’21). 2129–2134. Google ScholarCross Ref
- [53] . 2019. Robust embedding with multi-level structures for link prediction. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’19). 5240–5246.Google ScholarCross Ref
- [54] . 2019. Simplifying graph convolutional networks. In Proceedings of the International Conference on Machine Learning. PMLR, 6861–6871.Google Scholar
- [55] . 2020. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 1 (2020), 4–24.Google ScholarCross Ref
- [56] . 2018. Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. In Proceedings of the World Wide Web Conference. 187–196.Google ScholarDigital Library
- [57] . 2014. Embedding entities and relations for learning and inference in knowledge bases. Retrieved from https://arXiv:1412.6575.Google Scholar
- [58] . 2014. Detecting road traffic events by coupling multiple timeseries with a nonparametric bayesian method. IEEE Trans. Intell. Transport. Syst. 15, 5 (2014), 1936–1946.Google ScholarCross Ref
- [59] . 2017. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’17).Google Scholar
- [60] . 2018. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18). International Joint Conferences on Artificial Intelligence Organization, 3634–3640. Google ScholarCross Ref
- [61] . 2018. Netwalk: A flexible deep embedding approach for anomaly detection in dynamic networks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2672–2681.Google ScholarDigital Library
- [62] . 2016. Deep structured energy based models for anomaly detection. In Proceedings of the 33rd International Conference on International Conference on Machine Learning-Volume 48. 1100–1109.Google ScholarDigital Library
- [63] . 2020. Spatial-temporal convolutional graph attention networks for citywide traffic flow forecasting. In Proceedings of the 29th ACM International Conference on Information and; Knowledge Management (CIKM’20). ACM, New York, NY, 1853–1862. Google ScholarDigital Library
- [64] . 2021. Multiple dynamic graph based traffic speed prediction method. Neurocomputing 461 (2021), 109–117. Google ScholarDigital Library
- [65] . 2019. AddGraph: Anomaly detection in dynamic graph using attention-based temporal GCN. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’19). 4419–4425.Google ScholarCross Ref
- [66] . 2017. Anomaly detection with robust deep autoencoders. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 665–674.Google ScholarDigital Library
- [67] . 2020. Graph neural networks: A review of methods and applications. AI Open 1 (2020), 57–81.Google ScholarCross Ref
- [68] . 2018. Dynamic network embedding by modeling triadic closure process. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI’18). 571–578.Google ScholarCross Ref
- [69] . 2020. DeepAD: A joint embedding approach for anomaly detection on attributed networks. In Proceedings of the International Conference on Computational Science. Springer, 294–307.Google ScholarCross Ref
- [70] . 2018. Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In Proceedings of the International Conference on Learning Representations.Google Scholar
Index Terms
- Detecting Extreme Traffic Events Via a Context Augmented Graph Autoencoder
Recommendations
Unsupervised Anomaly Detection with a GAN Augmented Autoencoder
Artificial Neural Networks and Machine Learning – ICANN 2020AbstractAnomaly detection is a task of identifying samples that differ from the training data distribution. There are several studies that employ generative adversarial networks (GANs) as the main tool to detect anomalies using the rich contextual ...
Detecting Socially Abnormal Highway Driving Behaviors via Recurrent Graph Attention Networks
WWW '23: Proceedings of the ACM Web Conference 2023With the rapid development of Internet of Things technologies, the next generation traffic monitoring infrastructures are connected via the web, to aid traffic data collection and intelligent traffic management. One of the most important tasks in ...
Detecting spatiotemporal irregularities in videos via a 3D convolutional autoencoder
AbstractSpatiotemporal irregularities (i.e., the uncommon appearance and motion patterns) in videos are difficult to detect, as they are usually not well defined and appear rarely in videos. We tackle this problem by learning normal patterns ...
Comments