DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series Anomaly Detection (2401.11271v1)
Abstract: Anomaly detection in time-series data is crucial for identifying faults, failures, threats, and outliers across a range of applications. Recently, deep learning techniques have been applied to this topic, but they often struggle in real-world scenarios that are complex and highly dynamic, e.g., the normal data may consist of multiple distributions, and various types of anomalies may differ from the normal data to different degrees. In this work, to tackle these challenges, we propose Distribution-Augmented Contrastive Reconstruction (DACR). DACR generates extra data disjoint from the normal data distribution to compress the normal data's representation space, and enhances the feature extractor through contrastive learning to better capture the intrinsic semantics from time-series data. Furthermore, DACR employs an attention mechanism to model the semantic dependencies among multivariate time-series features, thereby achieving more robust reconstruction for anomaly detection. Extensive experiments conducted on nine benchmark datasets in various anomaly detection scenarios demonstrate the effectiveness of DACR in achieving new state-of-the-art time-series anomaly detection.
- “A review on outlier/anomaly detection in time series data,” ACM Computing Surveys, 2021.
- “Tcn-based lightweight log anomaly detection in cloud-edge collaborative environment,” in Tenth International Conference on Advanced Cloud and Big Data, 2022.
- “Robust anomaly detection for multivariate time series through stochastic recurrent neural network,” in ACM KDD, 2019.
- “Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding,” in ACM KDD, 2021.
- “Deep anomaly detection with outlier exposure,” in ICLR, 2018.
- “Drocc: Deep robust one-class classification,” in ICML, 2020.
- “Csi: Novelty detection via contrastive learning on distributionally shifted instances,” NeurIPS, 2020.
- “Neural transformation learning for deep anomaly detection beyond images,” in ICML, 2021.
- “Learning deep representations by mutual information estimation and maximization,” in ICLR, 2018.
- “Understanding contrastive representation learning through alignment and uniformity on the hypersphere,” in ICML, 2020.
- “Learning and evaluating representations for deep one-class classification,” in ICLR, 2020.
- “Robust outlier detection by de-biasing vae likelihoods,” in CVPR, 2022.
- “Lstm-based encoder-decoder for multi-sensor anomaly detection,” arXiv:1607.00148, 2016.
- “Tranad: Deep transformer networks for anomaly detection in multivariate time series data,” arXiv:2201.07284, 2022.
- “Non-transferable learning: A new approach for model ownership verification and applicability authorization,” in ICLR, 2021.
- “Unsupervised representation learning by predicting image rotations,” in ICLR, 2018.
- “Ts2vec: Towards universal representation of time series,” in AAAI, 2022.
- “Mean-shifted contrastive loss for anomaly detection,” arXiv:2106.03844, 2021.
- “Efficient stuttering event detection using siamese networks,” in ICASSP, 2023.
- “Graph neural network-based anomaly detection in multivariate time series,” in AAAI, 2021.
- “Unsupervised model selection for time series anomaly detection,” in ICLR, 2023.
- “Generic and scalable framework for automated time-series anomaly detection,” in ACM KDD, 2015.
- “Deja vu: Continual model generalization for unseen domains,” in ICLR, 2022.
- B Saha and K Goebel, “Nasa ames prognostics data repository,” NASA Ames, Moffett Field, CA, USA, 2007.
- “Calibrated one-class classification for unsupervised time series anomaly detection,” arXiv:2207.12201, 2022.