DeepFIB: Self-Imputation for Time Series Anomaly Detection
Not on the map. Why?
Abstract (arXiv)
Time series (TS) anomaly detection (AD) plays an essential role in various applications, e.g., fraud detection in finance and healthcare monitoring. Due to the inherently unpredictable and highly varied nature of anomalies and the lack of anomaly labels in historical data, the AD problem is typically formulated as an unsupervised learning problem. The performance of existing solutions is often not satisfactory, especially in data-scarce scenarios. To tackle this problem, we propose a novel self-supervised learning technique for AD in time series, namely DeepFIB. We model the problem as a Fill In the Blank game by masking some elements in the TS and imputing them with the rest. Considering the two common anomaly shapes (point- or sequence-outliers) in TS data, we implement two masking strategies with many self-generated training samples. The corresponding self-imputation networks can extract more robust temporal relations than existing AD solutions and effectively facilitate identifying the two types of anomalies. For continuous outliers, we also propose an anomaly localization algorithm that dramatically reduces AD errors. Experiments on various real-world TS datasets demonstrate that DeepFIB outperforms state-of-the-art methods by a large margin, achieving up to 65.2% relative improvement in F1-score.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 12 Dec 2021.
Builds on
23 of 48 references.
References · 23
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
- 2016Colorful Image Colorizationcited by 1,113
- 2019Strategies for Pre-training Graph Neural Networkscited by 964
- 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
- 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
- 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
- 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
- 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
- 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
11 more
- 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
- 2020A review on outlier/anomaly detection in time series datacited by 187
- 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
- 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
- 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
- 2019NAOMI: Non-Autoregressive Multiresolution Sequence Imputationcited by 59
- 2020Time Series Change Point Detection with Self-Supervised Contrastive Predictive Codingcited by 58
- 2020Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligencecited by 39
- 2020Time Series Data Imputation: A Survey on Deep Learning Approachescited by 34
- 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
- 2017Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Networkcited by 28
Built on by
Citing papers per year: 2025: 2.
2 papers.