DBScholar

Back to papers

Substructure-aware Log Anomaly Detection

Summary: SLAD detects code-file-level log anomalies by mining representative graph substructures with Monte Carlo Tree Search, then distilling and softly pruning them for node inference. It preserves subtle event/structural/location changes while achieving 15× faster inference than substructure-based methods. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
14053
Venue
VLDB
Year
2025
Pagerank
5.1757914e-05
Overall Rank
10,019 | 31.27%
DOI
10.14778/3705829.3705840

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{tang_vldb25,
        title = {{Substructure-aware Log Anomaly Detection}},
        author = {Tang, Yanni and Zhang, Zhuoxing and Zhao, Kaiqi and Fang, Lanting and Li, Zhenhua and Chen, Wu},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {2},
        pages = {213--225},
        doi = {10.14778/3705829.3705840},
        url = {https://doi.org/10.14778/3705829.3705840},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank Citing Paper Year Venue Pagerank
10,507 Unseen Anomaly Detection from System Logs 2026 SIGMOD 5.093636e-05
10,909 LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation 2025 VLDB 5.093636e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 3 of 3 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