GNN在微服务故障诊断中未必比简单模型更有效。
Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?
- 设计无图结构的DiagMLP，仅保留多模态融合能力
- 在5个数据集上性能与顶尖GNN方法持平
- 适合评估模型创新时需考虑基础基线
图神经网络（GNN）被广泛用于微服务系统的故障诊断，基于其建模服务依赖关系的能力。然而，显式图结构的必要性尚未得到充分检验，现有评估常将预处理与架构贡献混淆。为分离出GNN的真实价值，我们提出DiagMLP，一种刻意简化、不依赖拓扑结构的基线模型，保留多模态融合能力但排除图建模。在五个数据集上的消融实验表明，DiagMLP在故障检测、定位和分类任务上与最先进的GNN方法性能相当。研究结果挑战了图结构不可或缺的普遍假设，揭示：(i) 预处理流程已编码关键依赖信息，(ii) GNN模块的增益主要来自多模态融合而非图建模本身。本工作倡导对模型复杂性进行系统性重评，并呼吁建立标准化基线协议以验证模型创新。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) are widely adopted for fault diagnosis in microservice systems, premised on their ability to model service dependencies. However, the necessity of explicit graph structures remains underexamined, as existing evaluations conflate preprocessing with architectural contributions. To isolate the true value of GNNs, we propose DiagMLP, a deliberately minimal, topology-agnostic baseline that retains multimodal fusion capabilities while excluding graph modeling. Through ablation experiments across five datasets, DiagMLP achieves performance parity with state-of-the-art GNN-based methods in fault detection, localization, and classification. These findings challenge the prevailing assumption that graph structures are indispensable, revealing that: (i) preprocessing pipelines already encode critical dependency information, and (ii) GNN modules contribute marginally beyond multimodality fusion. Our work advocates for systematic re-evaluation of architectural complexity and highlights the need for standardized baseline protocols to validate model innovations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。