一句话：提出 ARMOR，用模态专属非对称编码器与缺失感知门控融合，在模态缺失下仍稳健完成异常检测、故障分诊与根因定位。
微服务场景下的自动化故障管理依赖多模态数据（指标、日志、调用链）的联合优化，但现有统一框架普遍假设数据完整，而实际中网络波动与探针失效常导致模态缺失；用静态占位符填补会引入插补噪声，掩盖异常并降低诊断性能。为此，作者提出鲁棒自监督框架 ARMOR，包含两个关键设计：一是模态专属的非对称编码器，用于隔离指标、日志与调用链之间的分布差异；二是缺失感知的门控融合机制，借助可学习占位符与动态偏置补偿，避免不完整输入造成的跨模态干扰。ARMOR 以掩码引导重构的自监督自回归方式联合优化异常检测、故障分诊与根因定位三个任务，其中异常检测与根因定位无需故障标签，分诊仅需故障类型标注来训练下游分类器。实验表明，ARMOR 在数据完整时达到当前最优性能，并在严重模态缺失时仍保持稳健的诊断精度。
Automated incident management is critical for microservice reliability. While recent unified frameworks leverage multimodal data for joint optimization, they unrealistically assume perfect data completeness. In practice, network fluctuations and agent failures frequently cause missing modalities. Existing approaches relying on static placeholders introduce imputation noise that masks anomalies and degrades performance. To address this, we propose ARMOR, a robust self-supervised framework designed for missing modality scenarios. ARMOR features: (i) a modality-specific asymmetric encoder that isolates distribution disparities among metrics, logs, and traces; and (ii) a missing-aware gated fusion mechanism utilizing learnable placeholders and dynamic bias compensation to prevent cross-modal interference from incomplete inputs. By employing self-supervised auto-regression with mask-guided reconstruction, ARMOR jointly optimizes anomaly detection (AD), failure triage (FT), and root cause localization (RCL). AD and RCL require no fault labels, while FT relies solely on failure-type annotations for the downstream classifier. Extensive experiments demonstrate that ARMOR achieves state-of-the-art performance under complete data conditions and maintains robust diagnostic accuracy even with severe modality loss.
@inproceedings{paperbot12195,
title = {ARMOR: A Robust Self-Supervised Framework for Root Cause Analysis in Microservices under Missing Modality},
author = {Wenzhuo Qian and Hailiang Zhao and Ziqi Wang and Zhipeng Gao and Jiayi Chen and Zhiwei Ling and Shuiguang Deng},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834338}
}