DBScholar

Back to papers

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)

Paper ID
14017
Venue
VLDB
Year
2025
Pagerank
5.2755515e-05
Overall Rank
9,379 | 35.66%
DOI
10.14778/3725688.3725699

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{jacob_vldb25,
        title = {{Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domains}},
        author = {Jacob, Vincent and Diao, Yanlei},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {6},
        pages = {1691--1704},
        doi = {10.14778/3725688.3725699},
        url = {https://doi.org/10.14778/3725688.3725699},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
10,298 The Power of Anomaly Detection in Predictive Maintenance: [Experiments & Analysis] 2026 SIGMOD 5.093636e-05
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.

Previous Page 1 / 1 Next

Semantically Similar Papers