Saved in:
Bibliographic Details
Main Authors: Gao, Fei, Xin, Ruyue, Li, Xiaocui, Zhang, Yaqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.02766
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929750249832448
author Gao, Fei
Xin, Ruyue
Li, Xiaocui
Zhang, Yaqiang
author_facet Gao, Fei
Xin, Ruyue
Li, Xiaocui
Zhang, Yaqiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02766
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?
Gao, Fei
Xin, Ruyue
Li, Xiaocui
Zhang, Yaqiang
Software Engineering
Artificial Intelligence
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.
title Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2501.02766