Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?

TL;DR

This paper questions the effectiveness of GNNs in fault diagnosis for microservice systems by introducing a simple, topology-agnostic baseline that matches GNN performance, highlighting the importance of preprocessing and multimodal fusion.

Contribution

The paper introduces DiagMLP, a minimal baseline that isolates the impact of graph modeling, demonstrating that GNNs may not be necessary for effective fault diagnosis.

Findings

DiagMLP matches GNN performance in fault detection, localization, and classification.

Preprocessing pipelines encode critical dependency information, reducing GNN necessity.

GNN modules contribute marginally beyond multimodality fusion.

Abstract

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.