Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domains
Summary: Frames unsupervised multivariate time-series anomaly detection as domain generalization and introduces DIVAD, a domain-invariant VAE to learn representations robust to shifts in normal behavior across heterogeneous AIOps domains. Provides a unifying benchmark and reports 15–20% higher peak F1 on Exathlon with validation on an application-server dataset. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Vincent Jacob
- 2. Yanlei Diao
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,253 | Anomaly Detection in Time Series: A Comprehensive Evaluation | 2022 | VLDB | 0.00013032074 |
| 1,634 | Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series | 2021 | VLDB | 0.00011058945 |
| 2,290 | TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data | 2022 | VLDB | 9.0934125e-05 |
| 6,448 | Sintel: A Machine Learning Framework to Extract Insights from Signals | 2022 | SIGMOD | 5.0587973e-05 |
Previous
Page 1 / 1
Next