@inproceedings{han2023achieving,author={Han, Xiao and Zhang, Lu and Wu, Yongkai and Yuan, Shuhan},title={Achieving Counterfactual Fairness for Anomaly Detection},year={2023},booktitle={Pacific-Asia Conference on Knowledge Discovery and Data Mining},pages={55--66},}
CIKM’23
On Root Cause Localization and Anomaly Mitigation through Causal Inference
Xiao Han, Lu Zhang, Yongkai Wu, and Shuhan Yuan
In Proceedings of the 32nd ACM International Conference on Information & Knowledge Management, 2023
@inproceedings{han2023root,author={Han, Xiao and Zhang, Lu and Wu, Yongkai and Yuan, Shuhan},title={On Root Cause Localization and Anomaly Mitigation through Causal Inference},year={2023},booktitle={Proceedings of the 32nd ACM International Conference on Information \& Knowledge Management},}
BigData’23
LogGPT: Log Anomaly Detection via GPT
Xiao Han, Shuhan Yuan, and Mohamed Trabelsi
In 2023 IEEE International Conference on Big Data (Big Data), 2023
@inproceedings{han2023loggpt,author={Han, Xiao and Yuan, Shuhan and Trabelsi, Mohamed},title={LogGPT: Log Anomaly Detection via GPT},year={2023},booktitle={2023 IEEE International Conference on Big Data (Big Data)},}
2022
ICDM’22
Few-shot Anomaly Detection and Classification Through Reinforced Data Selection
Xiao Han, Depeng Xu, Shuhan Yuan, and Xintao Wu
In 2022 IEEE International Conference on Data Mining (ICDM), 2022
@inproceedings{han2022few,author={Han, Xiao and Xu, Depeng and Yuan, Shuhan and Wu, Xintao},title={Few-shot Anomaly Detection and Classification Through Reinforced Data Selection},year={2022},booktitle={2022 IEEE International Conference on Data Mining (ICDM)},pages={963--968},}
2021
CIKM’21
Unsupervised Cross-System Log Anomaly Detection via Domain Adaptation
Xiao Han, and Shuhan Yuan
In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021
Log anomaly detection, which focuses on detecting anomalous log records, becomes an active research problem because of its importance in developing stable and sustainable systems. Currently, many unsupervised log anomaly detection approaches are developed to address the challenge of limited anomalous samples. However, collecting enough data to train an unsupervised model is not practical when the system is newly deployed online. To tackle this challenge, we propose a transferable log anomaly detection (LogTAD) framework that leverages the adversarial domain adaptation technique to make log data from different systems have a similar distribution so that the detection model is able to detect anomalies from multiple systems. Experimental results show that LogTAD can achieve high accuracy on cross-system anomaly detection by using a small number of logs from the new system.
@inproceedings{han2021unsupervised,author={Han, Xiao and Yuan, Shuhan},title={Unsupervised Cross-System Log Anomaly Detection via Domain Adaptation},year={2021},booktitle={Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},pages={3068–3072},}
BigData’21
InterpretableSAD: Interpretable Anomaly Detection in Sequential Log Data
Xiao Han, He Cheng, Depeng Xu, and Shuhan Yuan
In 2021 IEEE International Conference on Big Data (Big Data), 2021
@inproceedings{han2021interpretablesad,author={Han, Xiao and Cheng, He and Xu, Depeng and Yuan, Shuhan},title={InterpretableSAD: Interpretable Anomaly Detection in Sequential Log Data},year={2021},booktitle={2021 IEEE International Conference on Big Data (Big Data)},pages={1183-1192},}