United We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909814501670912 |
|---|---|
| author | He, Minghua Duan, Chiming Xiao, Pei Jia, Tong Yu, Siyu Zhang, Lingzhe Hong, Weijie Han, Jin Wu, Yifan Li, Ying Huang, Gang |
| author_facet | He, Minghua Duan, Chiming Xiao, Pei Jia, Tong Yu, Siyu Zhang, Lingzhe Hong, Weijie Han, Jin Wu, Yifan Li, Ying Huang, Gang |
| contents | Log-based fault diagnosis is essential for maintaining software system availability. However, existing fault diagnosis methods are built using a task-independent manner, which fails to bridge the gap between anomaly detection and root cause localization in terms of data form and diagnostic objectives, resulting in three major issues: 1) Diagnostic bias accumulates in the system; 2) System deployment relies on expensive monitoring data; 3) The collaborative relationship between diagnostic tasks is overlooked. Facing this problems, we propose a novel end-to-end log-based fault diagnosis method, Chimera, whose key idea is to achieve end-to-end fault diagnosis through bidirectional interaction and knowledge transfer between anomaly detection and root cause localization. Chimera is based on interactive multi-task learning, carefully designing interaction strategies between anomaly detection and root cause localization at the data, feature, and diagnostic result levels, thereby achieving both sub-tasks interactively within a unified end-to-end framework. Evaluation on two public datasets and one industrial dataset shows that Chimera outperforms existing methods in both anomaly detection and root cause localization, achieving improvements of over 2.92% - 5.00% and 19.01% - 37.09%, respectively. It has been successfully deployed in production, serving an industrial cloud platform. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | United We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning He, Minghua Duan, Chiming Xiao, Pei Jia, Tong Yu, Siyu Zhang, Lingzhe Hong, Weijie Han, Jin Wu, Yifan Li, Ying Huang, Gang Software Engineering Log-based fault diagnosis is essential for maintaining software system availability. However, existing fault diagnosis methods are built using a task-independent manner, which fails to bridge the gap between anomaly detection and root cause localization in terms of data form and diagnostic objectives, resulting in three major issues: 1) Diagnostic bias accumulates in the system; 2) System deployment relies on expensive monitoring data; 3) The collaborative relationship between diagnostic tasks is overlooked. Facing this problems, we propose a novel end-to-end log-based fault diagnosis method, Chimera, whose key idea is to achieve end-to-end fault diagnosis through bidirectional interaction and knowledge transfer between anomaly detection and root cause localization. Chimera is based on interactive multi-task learning, carefully designing interaction strategies between anomaly detection and root cause localization at the data, feature, and diagnostic result levels, thereby achieving both sub-tasks interactively within a unified end-to-end framework. Evaluation on two public datasets and one industrial dataset shows that Chimera outperforms existing methods in both anomaly detection and root cause localization, achieving improvements of over 2.92% - 5.00% and 19.01% - 37.09%, respectively. It has been successfully deployed in production, serving an industrial cloud platform. |
| title | United We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2509.24364 |