TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data
Summary: TranAD applies attention-based Transformer encoders to multivariate time-series anomaly detection and diagnosis, combining focus-score self-conditioning with adversarial training for robust, fast inference. MAML enables data-efficient learning, outperforming baselines by up to 17% F1 while cutting training time 99%. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Shreshth Tuli (Imperial College London)
- 2. Giuliano Casale (Imperial College London)
- 3. Nicholas R. Jennings (Loughborough University)
BibTeX Citation
@article{tuli_vldb22,
title = {{TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data}},
author = {Tuli, Shreshth and Casale, Giuliano and Jennings, Nicholas R.},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {6},
pages = {1201--1214},
doi = {10.14778/3514061.3514067},
url = {https://doi.org/10.14778/3514061.3514067},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 20 of 20 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,102 | Elle: Inferring Isolation Anomalies from Experimental Observations | 2021 | VLDB | 0.00012004972 |
| 1,544 | Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series | 2021 | VLDB | 0.00010304574 |
| 1,629 | SAND: Streaming Subsequence Anomaly Detection | 2021 | VLDB | 0.00010036401 |
| 2,907 | Real-Time Distance-Based Outlier Detection in Data Streams | 2021 | VLDB | 7.8769563e-05 |
| 3,682 | openGauss: An Autonomous Database System | 2021 | VLDB | 7.1013922e-05 |
| 6,197 | GraphAn: Graph-based Subsequence Anomaly Detection | 2020 | VLDB | 5.8527203e-05 |
Previous
Page 1 / 1
Next