Last updated on Monday, October 06, 2025
@inproceedings{Wang2025FSE,
author = {Yuqing Wang and Mika V. M{\"a}ntyl{\"a} and
Serge Demeyer and Mutlu Beyaz{\i}t and
Joanna Kisaakye Jesse Nyss{\"o}l{\"a}},
booktitle = {Proceedings {FSE 2024} (ACM International Conference
on the Foundations of Software Engineering)},
title = {Cross-System Categorization of Abnormal Traces in
Microservice-Based Systems via Meta-Learning},
year = {2025},
abstract = {Microservice-based systems (MSS) may fail with
various fault types, due to their complex and dynamic
nature. While existing AIOps tools excel at detecting
abnormal traces and pinpointing the responsible
service(s), human efforts from practitioners are
still required for further root cause analysis (RCA)
to diagnose specific fault types and analyze failure
reasons for detected abnormal traces, particularly
when abnormal traces do not stem directly from
specific services. This paper presents TraFaultDia, a
novel framework aimed at automatically classifying
abnormal traces into precise fault categories for
different MSS. We approach the automatic
categorization of abnormal traces into fault types as
a series of multi-class classification tasks, each
task represents an attempt to classify detected
abnormal traces for a MSS. With the classification
results from TraFaultDia, practitioners can quickly
know fault types of abnormal traces and understand
their nature of failures and potential impacts,
thereby reducing the time and effort required for
manual analysis. TraFaultDia is trained on several
abnormal trace classification tasks with a few
labeled instances from a MSS using a meta-learning
approach. After training, TraFaultDia can quickly
adapt to new, unseen abnormal trace classification
tasks with a few labeled instances across MSS. We
evaluated TraFaultDia on two representative MSS,
TrainTicket and OnlineBoutique, with open datasets.
Our results show that, within the MSS it is trained
on, TraFaultDia achieves an average accuracy of
93.26\% and 85.2\% across 50 new, unseen abnormal
trace classification tasks for TrainTicket and
OnlineBoutique respectively, when provided with 10
labeled instances for each fault category per task in
each system. In the cross-system context, when
TraFaultDia is applied to a MSS different from the
one it is trained on, TraFaultDia gets an average
accuracy of 92.19\% and 84.77\% for the same set of
50 new, unseen abnormal trace classification tasks of
the respective system, also with 10 labeled instances
provided for each fault category per task in each
system.},
annote = {internationalconference},
top = {A* in CORE2023},
doi = {10.1145/3715742},
}