The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Nezha: Interpretable Fine-Grained Root Causes Analysis for Microservices on Multi-modal Observability Data
Abstract
Root cause analysis (RCA) in large-scale microservice systems is a critical and challenging task. To understand and localize root causes of unexpected faults, modern observability tools collect and preserve multi-modal observability data, including metrics, traces, and logs. Since system faults may manifest as anomalies in different data sources, existing RCA approaches that rely on single-modal data are constrained in the granularity and interpretability of root causes. In this study, we present Nezha, an interpretable and fine-grained RCA approach that pinpoints root causes at the code region and resource type level by incorporative analysis of multi-modal data. Nezha transforms heterogeneous multi-modal data into a homogeneous event representation and extracts event patterns by constructing and mining event graphs. The core idea of Nezha is to compare event patterns in the fault-free phase with those in the fault-suffering phase to localize root causes in an interpretable way. Practical implementation and experimental evaluations on two microservice applications show that Nezha achieves a high top1 accuracy (89.77%) on average at the code region and resource type level and outperforms state-of-the-art approaches by a large margin. Two ablation studies further confirm the contributions of incorporating multi-modal data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Nezha [37] jointly encodes metrics, logs, and traces into a shared space with contrastive alignment and performs graph-based reasoning to localize causally relevant services under noisy/partial observability.”
From TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices (2026) · cites this paper as [37]
Citations
Cites
USAD: UnSupervised Anomaly Detection on Multivariate Time Series
Audibert, J., Michiardi, P., Guyard, F., Marti, S., & Zuluaga, M. A. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403392 · Cited by 1,094 · cited 4×
“, USAD [2] and JumpStarter [43]) and monitor additional metrics beyond the P90 latency and success ratio to avoid missing faults.”
BackgroundInfluentialDrain: an online log parsing approach with fixed depth tree
He, P., Zhu, J., Zheng, Z., & Lyu, M. R. (2017) · 2017 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2017.13 · Cited by 943 · cited 2×
“Data Integrator adopts a state-of-the-art log parsing approach Drain [19] to extract the static log templates and dynamic log parameters from the raw log messages in a streaming manner.”
MethodSelf-citationVisualization of test information to assist fault localization
Jones, J. A., Harrold, M. J., & Stasko, J. (2002) · Proceedings/Proceedings - International Conference on Software Engineering · doi:10.1145/581339.581397 · Cited by 904
Log clustering based problem identification for online service systems
Lin, Q., Zhang, H., Lou, J.-G., Zhang, Y., & Chen, X. (2016) · Proceedings of the 38th International Conference on Software Engineering Companion · doi:10.1145/2889160.2889232 · Cited by 427
Zhou, X., Peng, X., Xie, T., Sun, J., Ji, C., Li, W., & Ding, D. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2018.2887384 · Cited by 410
MicroRCA: Root Cause Localization of Performance Issues in Microservices
Wu, L., Tordsson, J., Elmroth, E., & Kao, O. (2020) · NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium · doi:10.1109/noms47738.2020.9110353 · Cited by 265
Unsupervised Detection of Microservice Trace Anomalies through Service-Level Deep Bayesian Networks
Liu, P., Xu, H., Ouyang, Q., Jiao, R., Chen, Z., Zhang, S., Yang, J., Mo, L., Zeng, J., Xue, W., et al. (2020) · 2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre5003.2020.00014 · Cited by 252
DeepTraLog: trace-log combined microservice anomaly detection through graph-based deep learning
Zhang, C., Peng, X., Sha, C., Zhang, K., Fu, Z., Wu, X., Lin, Q., & Zhang, D. (2022) · Proceedings of the 44th International Conference on Software Engineering · doi:10.1145/3510003.3510180 · Cited by 207
Root Cause Analysis: A Tool for Total Quality Management
Wilson, P. F., Dell, L. D., & Anderson, G. F. (1996) · Journal For Healthcare Quality · doi:10.1111/j.1945-1474.1996.tb00823.x · Cited by 204
Identifying impactful service system problems via log analysis
He, S., Lin, Q., Lou, J.-G., Zhang, H., Lyu, M. R., & Zhang, D. (2018) · Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3236024.3236083 · Cited by 201
Research works printed but not linked: 8
- Michael Chow, David Meisner, Jason Flinn, Daniel Peek, and Thomas F. Wenisch. 2014. The Mystery Machine: End-to-end Performance Analysis of Large-scale Internet Services. In OSDI 2014. USENIX Association, 217–231.
- Rodrigo Fonseca, George Porter, Randy H. Katz, Scott Shenker, and Ion Stoica. 2007. X-Trace: A Pervasive Network Tracing Framework. In NSDI, 2007. USENIX, 271–284.
- Chang Lou, Peng Huang, and Scott Smith. 2020. Understanding, Detecting and Localizing Partial Failures in Large System Software. In NSDI 2020. USENIX Association, 559–574.
- Minghua Ma, Shenglin Zhang, Junjie Chen, Jim Xu, Haozhe Li, Yongliang Lin, Xiaohui Nie, Bo Zhou, Yong Wang, and Dan Pei. 2021. Jump-Starting Multivariate Time Series Anomaly Detection for Online Service Systems. In USENIX ATC 2021. USENIX Association, 413–426.
- Karthik Nagaraj, Charles Edwin Killian, and Jennifer Neville. 2012. Structured Comparative Analysis of Systems Logs to Diagnose Performance Problems. In NSDI 2012. USENIX Association, 353–366.
- Opentelemetry. 2023. Opentelemetry. https://opentelemetry.io Accessed Jan. 6, 2023
- Benjamin H Sigelman, Luiz Andre Barroso, Mike Burrows, Pat Stephenson, Manoj Plakal, Donald Beaver, Saul Jaspan, and Chandan Shanbhag. 2010. Dapper, a large-scale distributed systems tracing infrastructure.
- Apache SkyWalking. 2023. Apache SkyWalking. https://skywalking.apache.org Accessed Jan. 6, 2023
Cited by
Failure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysis
Zhang, S., Xia, S., Fan, W., Shi, B., Xiong, X., Zhong, Z., Ma, M., Sun, Y., & Pei, D. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3715005 · Cited by 57
MULAN: Multi-modal Causal Structure Learning and Root Cause Analysis for Microservice Systems
Zheng, L., Chen, Z., He, J., & Chen, H. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645442 · Cited by 127
“Train Ticket [51]: This dataset is a microservice system for railway ticketing service with 5 system faults.”
BackgroundMethodInfluentialSelf-citationChen, S., Long, X., Fan, J., & Jin, G. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111520 · Cited by 49
Interpretable Failure Localization for Microservice Systems Based on Graph Autoencoder
Sun, Y., Lin, Z., Shi, B., Zhang, S., Ma, S., Jin, P., Zhong, Z., Pan, L., Guo, Y., & Pei, D. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3695999 · Cited by 59
Faseeha, U., Syed, H. J., Samad, F., Zehra, S., & Ahmed, H. M. (2025) · IEEE Access · doi:10.1109/access.2025.3562125 · Cited by 74
“Frameworks like MDF [65], Metrofunnel [66], AET [68], SuanMing [69], BBMA [70], Nezha [71], KUNERVA [72], CDOF [73], ADOB [74], eBPFM [75], MSM [78], STEAM [80], CHAOSORCA [82], eBPFNM [83], and ADAM [90] support deployment in cloud environments.”
InfluentialFlow-of-action: SOP-enhanced LLM-based multi-agent system for root cause analysis
Pei, C., Wang, Z., Liu, F., Li, Z., Liu, Y., He, X., Kang, R., Zhang, T., Chen, J., Li, J., et al. (2025) · Companion Proceedings of the ACM on Web Conference 2025 · doi:10.1145/3701716.3715225 · Cited by 33
Liu, H., Huang, X., Jia, M., Jia, T., Han, J., Wu, Z., & Li, Y. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3411481 · Cited by 35
Self-citationYao, Z., Pei, C., Chen, W., Wang, H., Su, L., Jiang, H., Xie, Z., Nie, X., & Pei, D. (2024) · Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering · doi:10.1145/3663529.3663827 · Cited by 21
“Nezha [42] converts multi-modal data into events related to user requests and ranks the root causes based on the changes in statistics of the event patterns.”
BackgroundMethodInfluentialXie, Z., Zhang, S., Geng, Y., Zhang, Y., Ma, M., Nie, X., Yao, Z., Xu, L., Sun, Y., Li, W., et al. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671530 · Cited by 37
ART: A Unified Unsupervised Framework for Incident Management in Microservice Systems
Sun, Y., Shi, B., Mao, M., Ma, M., Xia, S., Zhang, S., & Pei, D. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3695495 · Cited by 71
“Thus, a large portion of automated incident management techniques primarily consists of anomaly detection (AD) [7, 22, 28, 36, 38, 41, 47, 55, 62, 63], failure triage (FT) [32, 35, 37, 48, 59, 61], and root cause localization (RCL) [6, 12, 16, 19, 34, 52, 57, 58, 64].”
A Survey on Failure Analysis and Fault Injection in AI Systems
Yu, G., Tan, G., Huang, H., Zhang, Z., Chen, P., Natella, R., Zheng, Z., & Lyu, M. R.-T. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3732777 · Cited by 51
Self-citationCOCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge
Li, Y., Wu, Y., Liu, J., Jiang, Z., Chen, Z., Yu, G., & Lyu, M. R.-T. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00234 · Cited by 49
“We deliberately refrained from comparing COCA with traditional [4], [29] and AIOps methodologies [2], [6], [68] that utilize fault-free data during the procedure.”
InfluentialSelf-citationHolistic Root Cause Analysis for Failures in Cloud-Native Systems Through Observability Data
Han, Y., Du, Q., Huang, Y., Li, P., Shi, X., Wu, J., Fang, P., Tian, F., & He, C. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3478759 · Cited by 16
“2) Baselines: We select 3 advanced comprehensive multi-modal approaches (i.e., Nezha [52], Eadro [50], and DiagFu-sion [51]) and 5 single-modality-based approaches (i.e., De-jaVu [39], CIRCA [29], TraceRCA [11], EnsRCA [38], and Microscope [22]).”
InfluentialZhang, X., Wang, Q., Li, M., Yuan, Y., Xiao, M., Zhuang, F., & Yu, D. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3629066 · Cited by 15
“In contrast to directly using raw data for root cause localization, Nezha [46] and DiagFusion [48] convert heterogeneous multimodal data into homogeneous event representations, performing joint analysis through event graphs to achieve root cause localization.”
Xie, S., Wang, J., He, H., Wang, Z., Zhao, Y., Zhang, N., & Li, B. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3734868 · Cited by 30
“Despite the success of single-modal failure diagnosis methods in many scenarios, some specific failures are difficult to identify using a single modality due to the limited information each modality provides [66].”
Tracemesh: Scalable and Streaming Sampling for Distributed Traces
Chen, Z., Jiang, Z., Su, Y., Lyu, M. R.-T., & Zheng, Z. (2024) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud62652.2024.00016 · Cited by 21
“We follow [27] to deploy these applications and inject faults to generate abnormal traces that correspond to edge-case system behaviors.”
BackgroundMethodSelf-citationZhang, W., Xin, R., Chen, P., Li, X., Bian, A., Zhao, Y., & Zhao, Z. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112844 · Cited by 17
Self-citationGiving Every Modality a Voice in Microservice Failure Diagnosis via Multimodal Adaptive Optimization
Lei, T., Zhang, S., Jia, Z., Sun, J., Ma, M., Li, Z., Sun, Y., Yang, C., Zhang, Y., & Pei, D. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3695489 · Cited by 37
TraStrainer: Adaptive Sampling for Distributed Traces with System Runtime State
Huang, H., Zhang, X., Chen, P., He, Z., Zhi-ming, C., Yu, G., Chen, H., & Sun, C. (2024) · Proceedings of the ACM on software engineering. · doi:10.1145/3643748 · Cited by 17
Self-citationLO2: Microservice API Anomaly Dataset of Logs and Metrics
Bakhtin, A., Nyyssölä, J., Wang, Y., Ahmad, N., Ping, K., Esposito, M., Mäntylä, M., & Taibi, D. (2025) · doi:10.1145/3727582.3728682 · Cited by 20
LogLead - Fast and Integrated Log Loader, Enhancer, and Anomaly Detector
Mäntylä, M., Wang, Y., & Nyyssölä, J. (2024) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner60148.2024.00046 · Cited by 21
“As a compromise, we aim to enforce standardized names for columns holding the same type of data across different logs.”
MethodChangeRCA: finding root causes from software changes in large online systems
Yu, G., Chen, P., He, Z., Yan, Q., Luo, Y., Li, F., & Zheng, Z. (2024) · Proceedings of the ACM on Software Engineering · doi:10.1145/3643728 · Cited by 9
“However, existing RCA approaches [17, 23, 52, 54, 56] primarily rely on observability data, such as metrics and traces, while often neglecting the significance of change data.”
Self-citationKPIRoot: Efficient Monitoring Metric-based Root Cause Localization in Large-scale Cloud Systems
Gu, W., Sun, X., Liu, J., Huo, Y., Chen, Z., Zhang, J., Gu, J., Yang, Y., & Lyu, M. R.-T. (2024) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre62328.2024.00046 · Cited by 14
“In particular, a practical root cause localization approach for KPIs from cloud systems should meet the efficiency and interpretability requirements [12].”
Evidence-Verified Root Cause Localization for Microservice Incidents under Tool and Telemetry Noise
Ren, L., Tang, Y., Chen, B., Tao, J., & Chen, F. (2026) · International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) · doi:10.1109/mlise70044.2026.11607508 · Cited by 9
“A. Datasets and Fault Regrouping RE2 OnlineBoutique (OB) [10]: 12-service e-commerce application with 90 fault injection scenarios across 5 services and 6 fault types (CPU hog, memory leak, disk I/O stress, network delay, socket error, packet loss), yielding 15 incidents per fault type.”
SparseRCA: Unsupervised Root Cause Analysis in Sparse Microservice Testing Traces
Yao, Z., Ye, H., Pei, C., Cheng, G., Wang, G., Liu, Z., Chen, H., Cui, H., Li, Z., Li, J., et al. (2024) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre62328.2024.00045 · Cited by 14
“In detail, Nezha [31] fails to learn the event support for many patterns in its construction and testing stage, and CIRCA [47] fails to access continuous data traffic during structural graph construction and hypothesis testing.”
InfluentialSelf-citationFamos: Fault Diagnosis for Microservice Systems Through Effective Multi-Modal Data Fusion
Duan, C., Yang, Y., Jia, T., Liu, G., Liu, J., Zhang, H., Zhou, Q., Li, Y., & Huang, G. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00073 · Cited by 26
Self-citationGomes, F., Rêgo, P. A. L., & Trinta, F. A. M. (2025) · Computing · doi:10.1007/s00607-025-01540-w · Cited by 22
Tracezip: Efficient Distributed Tracing via Trace Compression
Chen, Z., Pu, J., & Zheng, Z. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3728888 · Cited by 14
Self-citationAutonomic Microservice Management via Agentic AI and MAPE-K Integration
Esposito, M., Bakhtin, A., Ahmad, N., Robredo, M., Su, R., Lenarduzzi, V., & Taibi, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04403-7_11 · Cited by 13
Interaction Prediction and Anomaly Detection in a Microservices-based Telecommunication Platform
Aktaş, K., & Kılınç, H. H. (2024) · doi:10.1145/3666015.3666017 · Cited by 11
Making Fault Localization in Online Service Systems More Actionable and Interpretable
Xv, K., Guo, S., Li, H., Li, C., Chen, R., Li, X., & Jiang, H. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3714466 · Cited by 11
“However, such approaches hinder the interpretability of the models.”
Self-citationIntegrating Time Series Anomaly Detection Into DevOps Workflows
Kånåhols, G., Hasan, S., & Strandberg, P. E. (2025) · IEEE Access · doi:10.1109/access.2025.3550665 · Cited by 11
“Yu et al. [23] introduced Nezha, an interpretable method for root cause analysis using multi-modal observatory data, with both the data and method made publicly available.”
End-to-end log statement generation at block-level
Fu, Y., Yan, M. L., He, P., Liu, C., Zhang, X., & Yang, D. (2024) · Journal of Systems and Software · doi:10.1016/j.jss.2024.112146 · Cited by 7
Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features
Gu, W., Liu, J., Chen, Z., Zhang, J., Su, Y., Gu, J., Feng, C. Q., Yang, Z., Yang, Y., & Lyu, M. R.-T. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3702978 · Cited by 16
Self Adjusting Log Observability for Cloud Native Applications
Pathak, D., Verma, M., Chakraborty, A., & Kumar, H. (2024) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud62652.2024.00061 · Cited by 8
“This approach is extensively implemented in large-scale modern microservices-based applications [12] and infrastructures, particularly for their self-healing capabilities.”
BackgroundCauselens: Causality-Based Interpretable Root Cause Analysis for Microservice Systems
Liu, Q., Chen, P., Yu, G., Lai, Y., & Li, X. (2025) · International Workshop on Quality of Service · doi:10.1109/iwqos65803.2025.11143407 · Cited by 7
“Metrics are time series of numeric values, including system metrics and business Key Performance Indicators (KPIs) [20], [21].”
Self-citationLeveraging multi-agent framework for root cause analysis
Fu, F., Ding, H., Qin, Y., Yu, J., & Xu, D. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02096-0 · Cited by 12
iTCRL: Causal-Intervention-Based Trace Contrastive Representation Learning for Microservice Systems
Tian, X., Ying, S., Li, T., Yuan, M., Wang, R., Zhao, Y., & Shang, J. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3446532 · Cited by 5
“OnlineBoutique (OB) [26].”
KAIOPS: A Platform Solution of End-to-End Multi-Modal AIOps for AI Training at Scale
Wang, Z., Liu, J., Zhang, P., Sun, X., Wang, X., Wo, T., Hu, C., Song, C., Ouyang, J., & Yang, R. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00263 · Cited by 7
A Retrieval-Augmented Log-Metric-Trace Twin for Backend Failure Diagnosis
Liu, Z., Wu, K., Dang, S., & Yang, Y. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634314 · Cited by 5
“Nezha [7] constructs event graphs from heterogeneous observability data.”
TraceDAE: Trace-Based Anomaly Detection in Microservice Systems via Dual Autoencoder
Li, J., Ying, S., Li, T., & Tian, X. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3583213 · Cited by 10
“Anomaly detection and root cause localization in microser-vice systems have garnered significant attention over the years [7], [8], [9], [10], [11].”
Cross-System Categorization of Abnormal Traces in Microservice-Based Systems via Meta-Learning
Wang, Y., Mäntylä, M., Demeyer, S., Beyazıt, M., Kisaakye, J., & Nyyssölä, J. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3715742 · Cited by 8
“…lead to more targeted and efficient resource allocation: the right teams or tools can be promptly deployed to tackle specific abnormal traces, ensuring that expertise and resources are utilized optimally and not wasted on unsuitable tasks [Nedelkoski et al. 2019a; Yu et al. 2023; Zhou et al. 2018].”
InfluentialA Root Cause Localization Method Based on Event Call Chains for Microservices
Chen, Y., Xiao, Z., & Teng, F. (2024) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn63464.2024.10793332 · Cited by 4
“Based on the hipster dataset from Nezha [11], we organized dataset D2.”
InfluentialAdvanced AI-Driven Automation for Smarter Networks: The Modern Observability Advantage
Tzanettis, I., Kakkavas, G., Stylos, A., Mountakis, G., Zafeiropoulos, A., & Papavassiliou, S. (2025) · IEEE Communications Magazine · doi:10.1109/mcom.001.2500256 · Cited by 3
“The first is constructed in real time based on the incoming traces’ base tree structure [2], similar to the Event Graph (EG) described in [11].”
Gu, W., Zhong, R., Yu, G., Sun, X., Liu, J., Huo, Y., Chen, Z., Zhang, J., Gu, J., Yang, Y., et al. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10769-0 · Cited by 8
“In particular, a practical root cause localization approach for KPIs from cloud systems should meet the efficiency and interpretability requirements Yu et al (2023).”
Self-citationOnline Multi-Modal Root Cause Identification in Microservice Systems
Zheng, L., Chen, Z., & Chen, H. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401594 · Cited by 15
“(2) Online Boutique † [14]: A microservice system designed for e-commerce, including five system faults.”
Self-citationVerifyRCA: LLM-Guided but Evidence-Verified Root Cause Analysis for Microservice Backends
Ma, W., Yang, K., Liu, Z., Jiang, R., & Jiang, Y. (2026) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis70504.2026.11633469 · Cited by 6
“Modern cloud-native backends rely on microservice architectures that decompose monolithic applications into loosely coupled services communicating over the network [1].”
TORAI: Multi-source Root Cause Analysis for Blind Spots in Microservice Service Call Graph
Pham, L., Ha, H., Zhang, X., & Zhang, H. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3808137 · Cited by 15
Full stack optimization of microservice architecture: systematic review and research opportunity
Yang, M., Wang, X., Cai, B., Wang, Y., & Guo, Y. (2025) · Cluster Computing · doi:10.1007/s10586-025-05690-6 · Cited by 9
“Similarly, Yu et al. [151 ] propose a fine-grained root cause analysis approach based on multi-modal observability data, which mines patterns from event graphs and localizes root causes by comparing event patterns with expected execution paths.”
Tsubouchi, Y., & Tsuruta, H. (2024) · IEEE Access · doi:10.1109/access.2024.3374334 · Cited by 4
“Multimodal-based methods analyze two or more data sources (such as metrics, logs, and traces) and then delve into faults [73], [74].”
MethodDIA4M: A Tool to Streamline DevOps Processes of Distributed Cloud-Native Systems
Tarak, E., & Kılınç, H. H. (2024) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk63289.2024.10773447 · Cited by 4
“[2]–[5] For instance, existing systems such as log4j and Autopilot have been shown to have performance limitations that hinder detailed monitoring, which is crucial for effective quality assurance in distributed systems.”
Leveraging Petri Nets for Workflow Anomaly Detection in Microservice Architectures
Kamboj, P., Artho, C. V., Guanciale, R., Jabbarvand, R., & Godfrey, P. B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-94634-9_11 · Cited by 2
DistriAD: Distributed Anomaly Detection for Large-Scale Microservice Systems
Li, Y., Li, Q., Zhang, C., Wang, L., Wang, C., Bai, Z., Luo, H., Gao, T., Ma, K., & Pan, L. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00106 · Cited by 3
“Most research focus on the model training phase, but do not iteratively update the model post-training [5], [14], [15].”
Self-citationReconRCA: Root Cause Analysis in Microservices with Incomplete Metrics
Zhang, Z., Wang, J., Li, B., & Zhang, L. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00024 · Cited by 5
“Yu et al. [36] presented an interpretable fine-grained root cause localization method, Nezha, which identifies root causes at the code region and resource type levels.”
MHP-RCA: Multivariate Hawkes Process-based Root Cause Analysis in microservice systems
Zhang, Z., Wang, J., Li, B., Liu, Y., Wu, H., & Hung, P. C. K. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107938 · Cited by 2
Multimodal Anomaly Detection for Microservice Systems via Grassmann Manifolds-Based Graph Fusion
He, S., Feng, K., Meng, K., Xie, K., & Zhao, X. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3665382 · Cited by 4
“Nezha [17] builds an event graph to locate anomalies, providing a graphical explanation of root causes.”
A Decentralized Root Cause Localization Approach for Edge Computing Environments
Fernando, D., Rodríguez, M. V. R., & Buyya, R. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3668228 · Cited by 2
“In this section, we provide an overview of existing RCL techniques, examine their deployment patterns and the challenges of adapting cloud-based approaches to edge environments, present the fundamentals of the PPR algorithm, and discuss the effi-ciency aspects of existing RCL techniques.”
Xiao, Z., Liu, X., Ma, W., Li, X., & Liu, Z. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682084 · Cited by 12
“Joint analysis of multiple observability sources yields significantly higher RCA accuracy [2], prompting a wave of multimodal diagnosis frameworks [3][4][5].”
Self-citationAn Empirical Study of Production Incidents in Generative AI Cloud Services
Yan, H., Chen, Y., Ma, M., Wen, M., Lu, S., Zhang, S., Xu, T., Wang, R., Bansal, C., Rajmohan, S., et al. (2025) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre66568.2025.00044 · Cited by 4
United We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning
He, M., Duan, C., Xiao, P., Jia, T., Yu, S., Zhang, L., Hong, W., Han, J., Wu, Y., Li, Y., et al. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00061 · Cited by 10
“The purpose of root cause localization is to identify the fault that caused the failure and link it to specific log entries [44], [45].”
Self-citationHR-RCA: Hierarchical Localization of Root Causes with False Causality Removal
Yang, Z., Guo, Y., & Chen, Y. (2025) · World Conference on Computing and Communication Technologies (WCCCT) · doi:10.1109/wccct65447.2025.11028017 · Cited by 1
“Some studies process multimodal data as events [9], [10], which preserve contextual information but take a lot of time to build event templates.”
Smarter Root Cause Analysis: Enhancing BARO With Outlier Filtering and Ranking Refinement
Wang, Q., Tang, J., Dandekar, N., Pant, S., & Selvamani, S. A. (2025) · IEEE Access · doi:10.1109/access.2025.3602962 · Cited by 1
“As a result, recent research has intensively explored advanced RCA algorithms [3], [4], [5], [6] aimed at accelerating and improving diagnostic accuracy.”
Robust and Lightweight Root Cause Analysis for Microservice Metrics
Fukuda, N., Nozue, H., Oishi, H., & Tayama, K. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00023 · Cited by 1
“These benchmarks have been widely used in many previous studies [5], [7], [10], [12]–[14], [20], [25].”
ADSDx : Towards Automated Accident Diagnosis for High-level Autonomous Driving Systems
Huang, Z., Dai, J., Luo, M., Chen, Y., Sun, H., Zhang, Y., & Yang, M. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3783993 · Cited by 1
“Other studies [39, 44, 64–66] employ data-driven approaches, analyzing runtime data (e.g., program logs) from systems like microservices [39, 64, 66] and distributed storage systems [65] to identify potential faults.”
Application level observability for adaptive Edge to Cloud continuum systems
Kaddour, S. M., Jonglez, B., & Balouek‐Thomert, D. (2025) · IEEE/ACM International Conference on Utility and Cloud Computing (UCC) · doi:10.1145/3773274.3774855 · Cited by 1
“RootCauseAnalysis(RCA): Sketch-basedanomalydetection [14], multi-modal observability [23], dependency graphs [10], real-time anomaly propagation [22], and feature reduction [20] support RCA in cloud-edge systems [8].”
Failure Classification for Microservice Systems Based on Variational Graph Auto-Encoders
Sun, W., Chen, P., Chen, M. H., Li, H., Wang, Y., Huang, G., & Li, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5012-8_14 · Cited by 2
Self-citationLogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems
Jiang, Z., Liu, J., Li, Y., Huang, H., He, X., Zhang, T., Chen, J., Li, Y., Shi, R., & Lyu, M. R. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00272 · Cited by 5
“This practice is common across modern industrial systems ( e.g. , Google and WeChat) and widely used frameworks ( e.g. , Spring Cloud), where unique request IDs and other metadata are routinely injected into logs via structured logging [26].”
Self-citationCloudHeal: A Lightweight Online Learning Based Self-Healing Framework for Cloud-Native Systems
Yi, J., He, Z., Yang, W., & Chen, P. (2025) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds69199.2025.00023 · Cited by 1
“This method is simple, efficient, and widely used in prior research [15]–[17].”
Self-citationRootScan: Unveiling Microservice Anomalies through Fine-Grained, Interpretable Root Cause Analysis
Li, C., Ye, C., & Zhou, H. (2025) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds69199.2025.00024 · Cited by 3
“(Dataset A) Multimodal Fault Localization Dataset: This dataset is open-sourced by Nezha in 2023 [24], designed for microservices fault localization in two applications: On-lineBoutique [47] and TrainTicket [30].”
InfluentialZhou, Y., Shen, Y., & Li, B. (2025) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec66846.2025.00016 · Cited by 2
“…deployment data and dependency data of the system to construct a dependency graph with multimodal data, and utilizes GNN to generate a learned Nezha [21] unifies multimodal data into events and mines event patterns to compares event patterns in the no-fault phase with those in the faulty phase.”
Machine Learning Techniques in Microservices: A Systematic Mapping
Gonzalez, D. B., Sotelo, J. A., Márquez, G., & Visconti, M. (2025) · International Conference of the Chilean Computer Science Society (SCCC) · doi:10.1109/sccc67219.2025.11420492 · Cited by 1
Panorama: Unveiling Latent Dependencies for Microservice Autoscaling via Meta-learning
Anonymous, Feng, H., Liu, Y., Zheng, J., He, X., & Zheng, Z. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837485
“Microservice architectures enable independent scaling of individual services [6, 9, 37, 54].”
Self-citationLLMRCA: Multilevel Root Cause Analysis for LLM Applications Using Multimodal Observability Data
Tan, G., He, Z., Li, M., Huang, H., Wang, Y., Chen, P., Casale, G., & Zhang, C. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3806200 · Cited by 6
Self-citationCausalRCA: Causal Graph-Augmented Retrieval for Root Cause Analysis in Microservice Systems
Kou, J., Qing, Z., Wei, R., Xue, F., Huang, W., & Zhuang, H. (2026) · International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT) · doi:10.1109/eibdct69742.2026.11566729 · Cited by 3
“Nezha [13] compares event patterns between fault-free and fault-affected phases on a multi-modal dependency graph to achieve interpretable root cause localization.”
LLMGuard: Multi-Agent Fault Diagnosis for Reliable Language-Model-as-a-Service
Zhong, Y., Yu, G., Huang, Y., Fu, Q., Ren, R., Feng, C., Yang, Y., & Lyu, M. R. (2026) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn69566.2026.00018 · Cited by 2
Self-citationWhen LLMs Listen to Experts: Accurate Failure Diagnosis in Operating Systems
Zhao, Y., Zhang, S., Sun, Y., Gu, W., Sun, Y., Wang, L., Shi, L., Huang, C., Yang, G., Zhang, L., et al. (2026) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1145/3786583.3786852 · Cited by 4
“Toaddressthese challenges, recent research has explored automated failure diagnosis using machine learning and deep learning techniques, which analyze patterns in observability data to infer potential root causes [4, 17, 25, 30, 36, 42, 44, 46, 47, 49, 53].”
InfluentialAnoMod: A Dataset for Anomaly Detection and Root Cause Analysis in Microservice System
Ping, K., Mazhar, H. B., Wang, Y., Song, Y., & Mäntylä, M. (2026) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/3793302.3793324 · Cited by 2
Zeng, H., Chen, N., & Deng, T. (2024) · Asia-Pacific Symposium on Internetware · doi:10.1145/3671016.3671383 · Cited by 2
“In the future, we plan to further optimize the model to analyze multi-source heterogeneous and multimodal data [4, 27], and to integrate anomaly interpretation functions into the model.”
Fu, N., Cheng, G., Dai, G., Mei, H., Qiu, X., & Teng, Y. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112513 · Cited by 4
Wang, J., Chen, R., Wang, Y., Liao, X., Fan, Z., Wu, X., Wu, W., Liu, X., & Zhao, J. (2026) · 2026 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws72778.2026.00056 · Cited by 1
“Nezha [37] jointly encodes metrics, logs, and traces into a shared space with contrastive alignment and performs graph-based reasoning to localize causally relevant services under noisy/partial observability.”
AIOpsLab in Action: An Open Platform for AIOps Research
Ma, M., Clark, J., & Zhang, S. (2025) · Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering · doi:10.1145/3696630.3728619
MicroTR: Transaction Reproduction Fault Diagnosis Framework for Microservice on Multi-Source Data
Yao, X., Ma, Y.-H., Lu, Q.-C., Fu, X., Li, Q., Wang, W., & Bian, K. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033284 · Cited by 1
A fault diagnosis framework for microservice systems in cloud-native networks
Fu, N., Cheng, G., Dai, G., & Yue, T. E. N. G. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0034 · Cited by 2
Sanchez, B. R., Giamattei, L., Guerriero, A., Pietrantuono, R., & Malavolta, I. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112626 · Cited by 1
Cheng, L., Ge, J., Lv, Q., Li, T., & Wu, B. (2025) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc67675.2025.00030
“This dataset encompasses 18 distinct attributes related to the performance and resource utilization of microservices, including metrics such as CPU usage, memory consumption, network traffic, system call activities, latency percentiles, and workload operations [18].”
Ekhlasi, M., Fiorini, A., Dagenais, M., Ezzati‐Jivan, N., & Lamothe, M. (2025) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme64153.2025.00056 · Cited by 2
“However, earlier work [38, 39, 4] considers all spans to have the same effect on the total duration.”
InfluentialIdentifying Failure Root Causes for Cloud-Native Microservice Applications
Rouf, R., Kaleibar, F. J., Litoiu, M., Rasolroveicy, M., Nagar, S., Mohapatra, P., Gupta, P., & Watts, I. (2025) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) · doi:10.1109/acsos-c66519.2025.00028
“Yu et al. [15] use an event-pattern mining algorithm (which is called Nezha) to differentiate normal and abnormal states, aiming to identify root causes in an interpretable way using multi-modal observability data (logs, metrics, and traces).”
Huang, X., Liu, H., Wu, Y., Zhang, L., Jia, T., Li, Y., & Wu, Z. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3646329 · Cited by 9
“Yu et al. proposed Nezha [12], which transforms log, metric, and trace data into event data, connects the events in sequence according to the order of time, and then uses frequent item mining to identify the relationship between events that differ the most frequently before and after the anomaly as…”
Self-citationDALAD: Unsupervised Detection of Global and Local Anomalies in Microservice Systems
Tian, X., Ying, S., Li, T., Zhang, T., & Wang, Y. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3649198 · Cited by 2
“During the operation of microservice systems, anomalies are inevitable and varied due to their complexity and large scale [7], [8], [9], [10].”
InfluentialDing, K., Ma, Y., & Bian, K. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5012-8_13 · Cited by 2
Fault Localization Algorithm Based on Multimodal Contrastive and Causal Learning
Wu, J., Chang, Y., Zhang, Z., Li, W., & Yi, W. (2025) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa66321.2025.00012
“Although this paper reviews methods such as TraceRank, MicroRank, Deja Vu, and Eadro, which have a certain influence in the field of fault localization, we chose Dynotears [15] , Nezha [16] , and MicroHECL [1] .”
GraphAD: Enhancing Microservice Anomaly Detection with Trace and Metrics Graph Learning
Ji, X., Cai, Y., Zhang, W., Dong, L., Sun, M., & Zhang, K. (2025) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca65693.2025.00126
Hypergraph Neural Network-based Multi-Granular Root Cause Localization for Microservice Systems
Li, Y., Wang, L., Zhang, C., Li, Q., Rong, S., Wen, B., Li, X., Ma, K., Du, Q., Li, K., et al. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00099
“• Nezha [5] : The core idea is to integrate multimodal observable data, uniformly represent them as time-related homogeneous events, and build a global event graph.”
InfluentialSelf-citationAlertGuardian: Intelligent Alert Life-Cycle Management for Large-scale Cloud Systems
Yu, G., Mai, G., Wang, R., Li, R., Chen, P., Pan, L., & Xu, R. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00009 · Cited by 4
“To detect and address these failures promptly, modern cloud systems employ comprehensive monitoring mechanisms that continuously track the health of services, generating diverse monitoring data ( e.g. , key performance indicators (KPIs)) [5]–[8].”
Self-citationAutomated Proactive Logging Quality Improvement for Large-Scale Codebases
Li, Y.-L., Liu, J., Pu, J., Jiang, Z., Chen, Z., He, X., Zhang, T., Chen, J., Li, Y., Shi, R., et al. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00283 · Cited by 6
“In parallel, techniques for root cause analysis aim to construct causal graphs or trace dependencies from log event sequences to pinpoint the source of a failure [52], [58], [56].”
Self-citationTian, X., Ying, S., Li, T., Shi, C., & Xiao, D. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3796706
“However, as shown in Table 1, most existing studies [12, 13, 17–19, 30, 32, 36, 37] for fault diagnosis can only localize root causes at service level or metric level rather than investigating the causes behind superficial phenomena.”
InfluentialST-GraphRCA: A Root Cause Analysis Model for Spatio-Temporal Graph Propagation in IoT Edge Computing
Su, T., Mo, R., Gong, Y., & Wang, H. (2026) · Sensors · doi:10.3390/s26051474 · Cited by 1
Uncertainty-Aware Multimodal Anomaly Detection for Microservice Systems With Active Learning
Dou, H., Guo, S., Zou, L., Zhang, Y., Chen, P., & Zheng, Z. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3672587 · Cited by 2
“Following previous studies [11], [22], we adopt chaos engineering techniques to inject seven types of anomalies: CPU/memory/disk stress, service failure, database query exceptions, packet loss, and packet loss/delay.”
Self-citationToward Fine-Grained Unknown Anomaly Detection in Microservice Systems based on Multimodal Data
Wang, Z., Wei, Y., Chen, S., Jin, D., Tan, J., & Zhang, T. (2025) · International Conference on Information Communication and Software Engineering (ICICSE) · doi:10.1109/icicse66971.2025.11429925
“Although these methods have demonstrated notable success in their respective domains, they fundamentally exhibit limited detection accuracy when confronted with anomalies that manifest differently across distinct modalities [7].”
Modality-Agnostic Root Cause Analysis with Optimal Transport for 5G Core Network
Fukuda, N., Nozue, H., & Tayama, K. (2025) · Globecom · doi:10.1109/globecom59602.2025.11431736
“Recent studies [6], [7], [8] have demonstrated that integrating heterogeneous and multimodal telemetry data and leveraging the correlations among them surpasses single-modality approaches in capturing diverse system behaviors and interactions.”
Influential
Metadata
- Authors
- Yu, G., Chen, P., Li, Y., Chen, H., Li, X., & Zheng, Z.
- Affiliations
- Sun Yat-sen University (CN)
- Venue
- Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
- Publisher
- ACM
- Published
- 2023-11-30
- Pages
- 553-565
- OpenAlex
- W4389158453
- Cited by
- 140
- References
- 46
- Citations by year
- 2026: 59 · 2025: 58 · 2024: 23
- FWCI
- 42.18
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) (publishedVersion)
- Funders
- National Key Research and Development Program of China (2019YFB1804002)
- National Natural Science Foundation of China (No.62272495)
- Guangdong Basic and Applied Basic Research Foundation (No.2023B1515020054)
- CCF-Lenovo Blue Ocean Research Fund
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Keywords
- root cause analysis, microservices, event graphs, fault location, interpretable fault diagnosis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.