{"ID":2863358,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24364","arxiv_id":"2509.24364","title":"United We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning","abstract":"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.","short_abstract":"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 thre...","url_abs":"https://arxiv.org/abs/2509.24364","url_pdf":"https://arxiv.org/pdf/2509.24364v1","authors":"[\"Minghua He\",\"Chiming Duan\",\"Pei Xiao\",\"Tong Jia\",\"Siyu Yu\",\"Lingzhe Zhang\",\"Weijie Hong\",\"Jin Han\",\"Yifan Wu\",\"Ying Li\",\"Gang Huang\"]","published":"2025-09-29T07:03:23Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[]","has_code":false}